Optical fiber controller operation supervision system based on frequency converter control system

Abstract

The invention relates to the technical field of optical fiber control safety supervision, in particular to an optical fiber controller operation supervision system based on a frequency converter control system, which comprises a processor, an initialization module, an optical fiber sensing module, a multi-dimensional state evaluation module, a diagnosis positioning module and a rear-end visual module, according to the method, a multi-dimensional operation supervision system is constructed, the technical defect that the traditional supervision dimension is single is overcome, a parameter deviation degree + scene adaptability + historical association degree three-dimensional positioning feature system is constructed, and a matching score is calculated in combination with an abnormal parameter deviation degree, the current operation scene adaptability and a historical fault association rule; according to the method, fault types are accurately screened, candidate faults with similar matching scores are subjected to secondary verification through key verification parameters, a single fault and a composite fault are effectively distinguished, the fault types and positions are rapidly and accurately positioned by adopting a combination mode of fault feature initial matching and Bayesian reasoning fine positioning, and the troubleshooting efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of fiber optic control safety monitoring technology, and in particular to a fiber optic controller operation monitoring system based on a frequency converter control system. Background Technology

[0002] With the continuous improvement of industrial automation, frequency converters, as the core equipment for realizing motor speed regulation and energy-saving control, are widely used in many fields such as power, metallurgy, chemical industry, and intelligent manufacturing. In order to ensure the stable and efficient operation of the frequency converter control system, fiber optic controllers are usually configured to realize high-speed and anti-interference signal transmission. The operating status directly determines the transmission accuracy and real-time performance of the frequency converter control commands, which in turn affects the safety and reliability of the entire industrial production system.

[0003] Currently, the operation monitoring of fiber optic controllers mostly adopts traditional electrical signal detection methods, but there is a lack of comprehensive monitoring in terms of multiple dimensions, such as the communication connection status of the fiber optic controller, and the signal transmission quality, the device's own operating parameters (such as temperature and power supply voltage), and abnormal fault warnings. Meanwhile, in the complex electromagnetic environment of industrial sites, electrical signal detection is easily interfered with, resulting in inaccurate monitoring data and difficulty in accurately identifying potential faults in fiber optic controllers. This means that fault location efficiency is low. When a fiber optic controller malfunctions, it is impossible to quickly locate the type of fault (such as excessive fiber optic link loss, controller module failure, abnormal signal modulation and demodulation, etc.) and the location of the fault. A lot of time is required for manual troubleshooting, which prolongs the system downtime.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide an optical fiber controller operation monitoring system based on a frequency converter control system to solve the aforementioned technical defects.

[0006] The objective of this invention can be achieved through the following technical solution: a fiber optic controller operation monitoring system based on a frequency converter control system, comprising a processor, an initialization module, a fiber optic sensing module, a multi-dimensional status assessment module, a diagnostic positioning module, and a back-end visualization module; The initialization module presets and stores the monitoring parameter thresholds through the storage unit of the main control board; The fiber optic sensing module is used to collect multi-dimensional operational data of the fiber optic controller and perform data preprocessing to obtain a standardized regulatory dataset, which is then sent to the processor for storage. The multidimensional state assessment module is used to build a comprehensive assessment model, and at the same time, it performs weighted and integrated processing on the obtained scores, and outputs a state feedback list based on the judgment result of the output comprehensive score. Based on the status feedback list, the diagnostic positioning module initiates the fault positioning process and outputs a positioning report when the actual status is a warning status or a fault status. The backend visual module is used to respond to status feedback lists and location reports and display them immediately.

[0007] Preferably, the analysis process of the multidimensional state assessment module is as follows: Construct a fiber optic link quality assessment sub-model, a controller hardware status assessment sub-model, and a signal transmission matching degree assessment sub-model; A comprehensive evaluation model is obtained by fusing the fiber optic link quality evaluation sub-model, the controller hardware status evaluation sub-model, and the signal transmission matching degree evaluation sub-model. The preprocessed standardized regulatory dataset is input into the comprehensive evaluation model to obtain the fiber optic link quality score, controller hardware status score, and signal transmission matching score output by the fiber optic link quality evaluation sub-model, controller hardware status evaluation sub-model, and signal transmission matching score, respectively.

[0008] Preferably, the preset weighting coefficients of the fiber optic link quality score, controller hardware status score, and signal transmission matching score are retrieved, and a comprehensive score is obtained by weighted summation of the fiber optic link quality score, controller hardware status score, and signal transmission matching score with the corresponding preset weighting coefficients. Fiber optic link quality score × corresponding weight coefficient + controller hardware status score × corresponding weight coefficient + signal transmission matching score × corresponding weight coefficient = comprehensive score; Retrieve the preset comprehensive score range [Zmin, Zmax], perform discrimination processing on the comprehensive score, and obtain the result of normal state, warning state or fault state; Normal state, warning state, and fault state are collectively referred to as the current state. A state feedback list is constructed based on fiber optic link quality score, controller hardware status score, signal transmission matching score, and current state.

[0009] Preferably, the analysis process of the diagnostic positioning module is as follows: From the preprocessed standardized regulatory dataset, extract all parameters that exceed the preset normal threshold to form an abnormal parameter set; The extracted set of abnormal parameters is compared one by one with the feature parameters of all fault types in the preset fault feature library. The matching degree of each fault type is calculated as follows: matching degree = (number of matched abnormal parameters / total number of feature parameters of the fault type) × 100%. Fault types with matching degree ≥ preset matching degree are selected as candidate faults. If multiple fault types meet the matching degree condition, the top 3 fault types with the highest matching degree are included in the candidate fault list.

[0010] Preferably, based on the candidate fault list, a three-dimensional positioning feature system of parameter deviation, scenario adaptability, and historical correlation is constructed. The preset dimensions and weights of each feature are as follows: Parameter deviation (preset weight a1): Calculate the average deviation of the abnormal parameter corresponding to each candidate fault from the normal threshold (deviation = Σ|abnormal parameter value - threshold| / number of abnormal parameters); Scenario adaptability (preset weight a2): Combine the current inverter load level and operating environment temperature, query the historical fault scenario library, and calculate the occurrence frequency ratio of each candidate fault in the scenario as the scenario adaptability; Historical correlation (preset weight a3): Calculate the occurrence frequency ratio of each candidate fault in the past 6 months with the similarity of the current abnormal parameter combination ≥ preset similarity as the historical correlation. Among them, a1, a2, and a3 are all greater than zero, and a1+a2+a3=1.

[0011] Preferably, for each candidate fault, the matching score is calculated as: Matching score = Parameter deviation × a1 + Scene adaptability × a2 + Historical correlation × a3, where the data of each feature dimension are standardized to the [0,1] interval; If the matching score of a candidate fault is greater than or equal to the preset score threshold, and is greater than or equal to the preset threshold compared to the matching scores of other candidate faults, then it is directly determined as the final fault type. If multiple candidate fault scores are greater than or equal to the preset score threshold and the score difference is less than 0.1, a secondary verification is initiated: the key verification parameters corresponding to each candidate fault are retrieved. If the key verification parameter of a candidate fault exceeds the preset standard threshold, the fault is locked as the final fault type. If the final fault type is not obtained, it is determined to be a composite fault type. The composite fault type is the top two faults ranked by matching score.

[0012] Preferably, based on the determined final fault type or composite fault type, and combined with the fiber optic controller structure topology diagram, the physical connection relationship and location number of each link node are clearly defined in the structure topology diagram; at the same time, based on the determined final fault type or composite fault type, the corresponding positioning rule base is matched to clarify the core positioning dimensions and the required data types of detection, and the initially locked fault point is accurately mapped to the fiber optic controller structure topology diagram to determine the specific physical location and generate standardized location information. At the same time, the physical identifier of the fault location and surrounding related components are recorded to form a positioning report.

[0013] The beneficial effects of this invention are as follows: This invention constructs a multi-dimensional operation monitoring system, collecting multi-dimensional data such as fiber optic link transmission, controller hardware, signal modulation and demodulation, and inverter-related operation, to achieve comprehensive monitoring of the operating status of the fiber optic controller and overcome the shortcomings of traditional monitoring with only one dimension.

[0014] This invention also constructs a three-dimensional localization feature system of parameter deviation, scene adaptability, and historical correlation, breaking through the traditional single fault localization logic of parameter threshold comparison: it calculates the matching score by combining the degree of deviation of abnormal parameters, the adaptability of the current operating scene, and the historical fault correlation pattern to achieve accurate screening of fault types. For candidate faults with similar matching scores, secondary verification is performed through key verification parameters to effectively distinguish between single faults and compound faults, thus solving the problem of "different faults with the same symptoms" in traditional fault localization. Furthermore, it adopts a combination of initial fault feature matching and Bayesian inference for precise localization to quickly and accurately locate the fault type and location, improve fault troubleshooting efficiency, and shorten system downtime. Attached Figure Description

[0015] The invention will now be further described with reference to the accompanying drawings; Figure 1 This is a flowchart of the system of the present invention; Figure 2 This is a partial analysis reference diagram of Embodiment 1 of the present invention. Detailed Implementation

[0016] 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.

[0017] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments; Example 1: Please refer to Figures 1 to 2 As shown, the present invention is a fiber optic controller operation monitoring system based on a frequency converter control system, including a processor, an initialization module, a fiber optic sensing module, a multi-dimensional status assessment module, a diagnostic positioning module, and a back-end visualization module. The processor has bidirectional communication connections with the initialization module and the fiber optic sensing module, a unidirectional communication connection with the multi-dimensional status assessment module, a bidirectional communication connection with the diagnostic positioning module, and a unidirectional communication connection with the back-end visualization module. The initialization module presets and stores monitoring parameter thresholds through the storage unit of the main control board, including optical link loss threshold, core chip temperature threshold, power supply voltage threshold, and signal transmission matching degree threshold; it configures the data acquisition frequency reference value, presets a fault feature library, and stores the feature parameters corresponding to fault types (such as optical fiber link breakage, core chip overheating, abnormal power supply voltage, modem module failure, signal matching imbalance, etc.). The fiber optic sensing module is used to collect multi-dimensional operational data from the fiber optic controller (fiber optic link transmission parameters, signal modulation and demodulation parameters, and inverter-related operational data), perform data preprocessing to obtain a standardized regulatory dataset, and then send it to the processor for storage. Specifically, this includes: Data acquisition: Real-time acquisition of fiber optic link transmission parameters (such as transmission rate, signal attenuation, etc.), controller hardware operating parameters (such as core chip temperature, power supply voltage, etc.), signal modulation and demodulation parameters (such as modulation frequency, demodulation signal-to-noise ratio, etc.), and inverter-related operating data (such as output frequency, output voltage, etc.). Data preprocessing: First, the 3σ criterion is used to remove outlier data exceeding the mean ± 3 times the standard deviation. For example, when the core chip temperature detection value is 120℃, it exceeds the normal range (-20℃-85℃) and the mean ± 3 times the standard deviation, so it is removed. Then, a sliding window filtering method (window size set to 5) is used to remove noisy data. Subsequently, the min-max standardization method is used to map all data to the [0,1] interval to eliminate the influence of dimensions. Finally, weights are assigned according to the reliability of each data source (e.g., fiber optic link data weight 0.4, hardware data weight 0.3, modulation and demodulation data weight 0.2, inverter-related data weight 0.1), and a weighted average method is used to achieve multi-source data fusion to obtain a standardized regulatory dataset. The multidimensional state assessment module is used to construct a comprehensive assessment model, and simultaneously performs weighted and fusion processing on the obtained scores. Based on the judgment result of the output comprehensive score, it outputs a state feedback list, which specifically includes: Construct a fiber optic link quality assessment sub-model, a controller hardware status assessment sub-model, and a signal transmission matching degree assessment sub-model; The fiber optic link quality assessment sub-model uses standardized transmission rate, signal attenuation, bit error rate, and signal-to-noise ratio as input features. It employs a support vector machine algorithm and trains the model using training samples (including 500 sets each of normal and abnormal link data) to output a fiber optic link quality score of 0-100. The controller hardware status assessment sub-model uses standardized data of core chip temperature, power supply voltage, and operating current as input. It trains the model using a BP neural network (with 3 hidden layers and 10, 8, and 6 nodes respectively) and outputs a hardware operating status score of 0-100. Signal transmission matching evaluation sub-model: The model is trained using standardized data of modulation frequency, demodulation signal-to-noise ratio, signal amplitude deviation and inverter output frequency as input, and outputs a signal transmission matching score of 0-100. A comprehensive evaluation model is obtained by fusing the fiber optic link quality evaluation sub-model, the controller hardware status evaluation sub-model, and the signal transmission matching degree evaluation sub-model. The preprocessed standardized regulatory dataset is input into the comprehensive evaluation model to obtain the fiber optic link quality score, controller hardware status score, and signal transmission matching score output by the fiber optic link quality evaluation sub-model, controller hardware status evaluation sub-model, and signal transmission matching score, respectively. The preset weighting coefficients of the fiber optic link quality score, controller hardware status score, and signal transmission matching score are retrieved (such as the weighting coefficient of fiber optic link quality (0.4), the weighting coefficient of hardware working status (0.3), and the weighting coefficient of signal transmission matching (0.3)). The comprehensive score is obtained by weighting and summing the fiber optic link quality score, controller hardware status score, and signal transmission matching score with the corresponding preset weighting coefficients. That is, the comprehensive score is calculated as follows: fiber optic link quality score × corresponding weight coefficient + controller hardware status score × corresponding weight coefficient + signal transmission matching score × corresponding weight coefficient. The preset comprehensive score range [Zmin, Zmax] is retrieved, and the comprehensive score is judged. If the comprehensive score > Zmax, it is judged as a normal state; if the comprehensive score ∈ [Zmin, Zmax], it is judged as a warning state; if the comprehensive score < Zmin, it is judged as a fault state. Normal state, warning state and fault state are collectively referred to as actual state. A state feedback list is constructed based on fiber optic link quality score, controller hardware status score, signal transmission matching degree score and actual state. For example, if at a certain moment the fiber optic link quality score is 80, the hardware working status score is 75, and the signal transmission matching score is 70, the comprehensive score is 80×0.4+75×0.3+70×0.3=75.5, which is judged as a warning state. The backend visualization module is used to respond to the status feedback list and display it immediately, so that operation and management personnel can intuitively understand the operation monitoring results of the fiber optic controller, which will help to manage it in a more rational way.

[0018] Example 2: Based on the status feedback list, the diagnostic positioning module initiates the fault positioning process and outputs a positioning report when the actual status is a warning state or a fault state. The specific fault positioning process is as follows: S1: Extract all parameters that exceed the preset normal threshold from the preprocessed standardized monitoring dataset to form an abnormal parameter set, and clarify the specific value of each abnormal parameter and the degree of deviation from the threshold (e.g., signal attenuation of 18dB, exceeding the upper limit of the normal threshold by 3dB; core chip temperature of 88℃, exceeding the upper limit of the normal threshold by 3℃); at the same time, extract the inverter operating load data (e.g., load current, output frequency) and fiber optic controller operating mode information at that moment as a matching auxiliary basis; S2: Compare the extracted set of abnormal parameters with the feature parameters of all fault types in the preset fault feature library one by one, and calculate the matching degree of each fault type. The matching degree = (number of matched abnormal parameters / total number of feature parameters of the fault type) × 100%. Select fault types with a matching degree ≥ preset matching degree as candidate faults. If multiple fault types meet the matching degree condition, select the top 3 fault types with the highest matching degree and include them in the candidate fault list. At the same time, record the matching parameters, unmatched parameters, and specific matching degree values ​​of each candidate fault (e.g., "excessive fiber loss" with a matching degree of 80%, and matching parameters are signal attenuation of 12dB and bit error rate of 5×10). -6 (The unmatched auxiliary parameter is a signal-to-noise ratio of 32dB). S3: Based on the candidate fault list, construct a three-dimensional positioning feature system of parameter deviation, scenario adaptability, and historical correlation. The preset dimensions and weights of each feature are as follows: Parameter deviation (preset weight a1): Calculate the average deviation of the abnormal parameter corresponding to each candidate fault from the normal threshold (deviation = Σ|abnormal parameter value - threshold| / number of abnormal parameters); Scenario adaptability (preset weight a2): Combine the current inverter load level and operating environment temperature, query the historical fault scenario library, and calculate the occurrence frequency ratio of each candidate fault in the scenario as the scenario adaptability; Historical correlation (preset weight a3): Calculate the occurrence frequency ratio of each candidate fault in the past 6 months with the similarity of the current abnormal parameter combination ≥ preset similarity as the historical correlation. Among them, a1, a2, and a3 are all greater than zero, and a1+a2+a3=1. S4: For each candidate fault, the matching score is calculated as follows: Matching score = Parameter deviation × a1 + Scenario adaptability × a2 + Historical correlation × a3, where the data of each feature dimension are standardized to the [0,1] interval (parameter deviation is normalized according to the "maximum deviation value", and scenario adaptability and historical correlation are directly calculated as percentages). For example, the parameter deviation of a candidate fault "excessive fiber loss" is 0.8, the scenario adaptability is 0.6, and the historical correlation is 0.7. Its weighted voting score = 0.8 × 0.5 + 0.6 × 0.3 + 0.7 × 0.2 = 0.72. S5: If the matching score of a candidate fault is greater than or equal to the preset score threshold, and is greater than or equal to the preset threshold compared to the matching scores of other candidate faults, then it is directly determined as the final fault type. If multiple candidate fault scores are greater than or equal to the preset score threshold and the score difference is less than 0.1, a secondary verification is initiated: the key verification parameters corresponding to each candidate fault are retrieved (e.g., the verification parameter for fiber optic link faults is "optical power value", and the verification parameter for hardware faults is "module cooling fan speed"). If the key verification parameter of a candidate fault exceeds the preset standard threshold, the fault is locked as the final fault type. If the final fault type is not obtained, it is determined to be a composite fault type. The composite fault type is the top two faults ranked by matching score, such as fiber optic link faults + hardware faults. S6: Based on the determined final fault type or composite fault type, and in conjunction with the fiber optic controller structure topology diagram, clearly define the physical connection relationship, location number, and other information of each link node in the structure topology diagram; Fault type and location rule matching: Based on the determined final fault type or composite fault type, match the corresponding location rule base to clarify the core location dimensions and the required data types for detection. If the fault is related to the fiber optic link (such as link breakage or excessive loss), the specific length of the fault point from the transmitter is determined by synchronously collecting fiber optic link detection data using an optical time domain reflectometer (OTDR) (error ≤ 1m). This data is then used to map the specific link node (e.g., "fiber optic connection port P2, 15m from the transmitter"). If it is a hardware fault (such as overheating of the core chip or abnormal power supply), locate the specific hardware module and pin, such as "core chip U1 (model XXX), abnormal voltage of power supply pin VCC1"; If the fault is in the modem module, locate the specific functional module of the modem unit (e.g., "Demodulation module D1, signal amplification circuit fault"). If the signal mismatch is the cause, locate the signal adaptation unit and determine whether the abnormality is at the modulation frequency configuration end or the frequency feedback end of the inverter. At the same time, record the physical identifier of the fault location (such as module number, port number, link segment number) and surrounding related components to facilitate on-site troubleshooting by staff. Topology mapping and precise location information output: The initially identified fault points are precisely mapped to the fiber optic controller's structural topology to determine their specific physical locations and generate standardized location information. Fiber optic link type: Output "Fault module (fiber optic transmission module M2) - link node (port P2) - specific location (armored fiber optic connector 15m from the transmitter)"; Hardware: Output "Fault Module (Main Control Module M1) - Component Model (Core Chip U1, Model XC6SLX9-PQFG144) - Specific Location (Power Supply Pin VCC1)"; Modulation / demodulation module type: Output "Fault module (modulation / demodulation unit M3) - functional sub-module (demodulation module D1) - specific location (signal amplification circuit)"; Signal mismatch type: Output "Fault module (signal adapter unit M4) - specific location (modulation frequency configuration terminal J3 interface)"; Simultaneously, the physical location of the fault and surrounding related components (such as adjacent interfaces and fixing screw positions) are recorded to form a location report. The back-end visual module responds to and displays the location report, which facilitates quick on-site troubleshooting by staff. In summary, this system constructs a multi-dimensional operation monitoring system, collecting data from various dimensions such as fiber optic link transmission, controller hardware, signal modulation and demodulation, and inverter-related operations. This enables comprehensive monitoring of the fiber optic controller's operational status, overcoming the shortcomings of traditional single-dimensional monitoring. Furthermore, it constructs a three-dimensional positioning feature system combining parameter deviation, scenario adaptability, and historical correlation, breaking through the traditional single-fault location logic of parameter threshold comparison. By combining the degree of abnormal parameter deviation, current operational scenario adaptability, and historical fault correlation patterns to calculate matching scores, it achieves accurate screening of fault types. For candidate faults with similar matching scores, secondary verification is performed using key verification parameters to effectively distinguish between single and compound faults, solving the problem of "different faults with the same symptoms" in traditional fault location. Finally, it employs a combination of initial fault feature matching and Bayesian inference for precise positioning, quickly and accurately locating fault types and locations, improving fault troubleshooting efficiency, and shortening system downtime.

[0019] The threshold is set for comparative analysis of results to determine whether they are good or bad. The value of the threshold is determined by a combination of large-scale model analysis of sample data and human experience. It can also be adjusted appropriately based on seasonal or common-sense influencing factors.

[0020] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A fiber optic controller operation monitoring system based on a frequency converter control system, characterized in that, It includes a processor, an initialization module, a fiber optic sensing module, a multi-dimensional status assessment module, a diagnostic positioning module, and a back-end visualization module; The initialization module presets and stores the monitoring parameter thresholds through the storage unit of the main control board; The fiber optic sensing module is used to collect multi-dimensional operational data of the fiber optic controller and perform data preprocessing to obtain a standardized regulatory dataset, which is then sent to the processor for storage. The multidimensional state assessment module is used to build a comprehensive assessment model, and at the same time, it performs weighted and integrated processing on the obtained scores, and outputs a state feedback list based on the judgment result of the output comprehensive score. Based on the status feedback list, the diagnostic positioning module initiates the fault positioning process and outputs a positioning report when the actual status is a warning status or a fault status. The backend visual module is used to respond to status feedback lists and location reports and display them immediately.

2. The fiber optic controller operation monitoring system based on a frequency converter control system according to claim 1, characterized in that, The analysis process of the multidimensional state assessment module is as follows: Construct a fiber optic link quality assessment sub-model, a controller hardware status assessment sub-model, and a signal transmission matching degree assessment sub-model; A comprehensive evaluation model is obtained by fusing the fiber optic link quality evaluation sub-model, the controller hardware status evaluation sub-model, and the signal transmission matching degree evaluation sub-model. The preprocessed standardized regulatory dataset is input into the comprehensive evaluation model to obtain the fiber optic link quality score, controller hardware status score, and signal transmission matching score output by the fiber optic link quality evaluation sub-model, controller hardware status evaluation sub-model, and signal transmission matching score, respectively.

3. The fiber optic controller operation monitoring system based on a frequency converter control system according to claim 2, characterized in that, The preset weighting coefficients of the fiber optic link quality score, controller hardware status score, and signal transmission matching score are retrieved, and a comprehensive score is obtained by weighted summation of the fiber optic link quality score, controller hardware status score, and signal transmission matching score with the corresponding preset weighting coefficients. Fiber optic link quality score × corresponding weight coefficient + controller hardware status score × corresponding weight coefficient + signal transmission matching score × corresponding weight coefficient = comprehensive score; Retrieve the preset comprehensive score range [Zmin, Zmax], perform discrimination processing on the comprehensive score, and obtain the result of normal state, warning state or fault state; Normal state, warning state, and fault state are collectively referred to as the current state. A state feedback list is constructed based on fiber optic link quality score, controller hardware status score, signal transmission matching score, and current state.

4. The fiber optic controller operation monitoring system based on a frequency converter control system according to claim 1, characterized in that, The analysis process of the diagnostic localization module is as follows: From the preprocessed standardized regulatory dataset, extract all parameters that exceed the preset normal threshold to form an abnormal parameter set; The extracted set of abnormal parameters is compared one by one with the feature parameters of all fault types in the preset fault feature library. The matching degree of each fault type is calculated as follows: matching degree = (number of matched abnormal parameters / total number of feature parameters of the fault type) × 100%. Fault types with matching degree ≥ preset matching degree are selected as candidate faults. If multiple fault types meet the matching degree condition, the top 3 fault types with the highest matching degree are included in the candidate fault list.

5. The fiber optic controller operation monitoring system based on a frequency converter control system according to claim 4, characterized in that, Based on the candidate fault list, a three-dimensional localization feature system is constructed, consisting of parameter deviation, scenario adaptability, and historical correlation. The preset dimensions and weights of each feature are as follows: Parameter deviation (preset weight a1): Calculate the average deviation of the abnormal parameter corresponding to each candidate fault from the normal threshold (deviation = Σ|abnormal parameter value - threshold| / number of abnormal parameters); Scenario adaptability (preset weight a2): Combine the current inverter load level and operating environment temperature, query the historical fault scenario library, and calculate the occurrence frequency ratio of each candidate fault in the scenario as the scenario adaptability; Historical correlation (preset weight a3): Calculate the occurrence frequency ratio of each candidate fault within the past 6 months based on the historical fault records with a similarity ≥ preset similarity to the current abnormal parameter combination, and use this as the historical correlation. Here, a1, a2, and a3 are all greater than zero, and a1 + a2 + a3 = 1.

6. The fiber optic controller operation monitoring system based on a frequency converter control system according to claim 5, characterized in that, For each candidate fault, the matching score is calculated as follows: Matching score = Parameter deviation × a1 + Scenario adaptability × a2 + Historical correlation × a3, where the data of each feature dimension are standardized to the [0,1] interval. If the matching score of a candidate fault is greater than or equal to the preset score threshold, and is greater than or equal to the preset threshold compared to the matching scores of other candidate faults, then it is directly determined as the final fault type. If multiple candidate fault scores are greater than or equal to the preset score threshold and the score difference is less than 0.1, a secondary verification is initiated: the key verification parameters corresponding to each candidate fault are retrieved. If the key verification parameter of a candidate fault exceeds the preset standard threshold, the fault is locked as the final fault type. If the final fault type is not obtained, it is determined to be a composite fault type. The composite fault type is the top two faults ranked by matching score.

7. The fiber optic controller operation monitoring system based on a frequency converter control system according to claim 6, characterized in that, Based on the determined final fault type or composite fault type, and in conjunction with the fiber optic controller structure topology diagram, the physical connection relationship and location number of each link node are clearly defined in the structure topology diagram. At the same time, based on the determined final fault type or composite fault type, the corresponding location rule base is matched to clarify the core location dimensions and the required data types of detection. The initially identified fault points are accurately mapped to the fiber optic controller structure topology diagram to determine the specific physical location and generate standardized location information. At the same time, the physical identifier of the fault location and surrounding related components are recorded to form a location report.

Images