Offshore wind plant operation and maintenance management system

Abstract

The invention provides an operation and maintenance management system for an offshore wind power plant, which relates to the technical field of wind power generation and comprises a data acquisition and transmission module for acquiring equipment operation parameters in real time by utilizing Internet of Things equipment and transmitting the equipment operation parameters to a target data platform; according to the abnormity identification module, the target data platform performs abnormity identification based on the received equipment operation parameters to obtain an abnormity analysis result; the intelligent decision-making module is used for generating maintenance suggestions for processing according to the exception analysis result; and the remote monitoring module is used for monitoring the operation condition and the maintenance condition of the target equipment in real time by operation and maintenance personnel. The method comprises the following steps: transmitting equipment operation parameters acquired in real time to a target data platform; the target data platform performs equipment abnormity identification and generates maintenance suggestions for corresponding processing based on the received equipment operation parameters; operation and maintenance personnel monitor the operation condition and the equipment maintenance condition of the target equipment in real time, the accuracy and scientificity of operation and maintenance management of the offshore wind power plant can be effectively improved, and then the operation and maintenance efficiency of offshore operation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to an offshore wind farm operation and maintenance management system. Background Art

[0002] In recent years, with the explosive growth of domestic offshore wind power, the demand for operation and maintenance of offshore wind farms has increased. However, offshore wind farms have inconvenient transportation and poor accessibility. In addition, my country's offshore wind power industry started late and has little accumulated experience, which has led to many problems in the operation and maintenance of offshore wind farm equipment and low efficiency of offshore operation and maintenance. Therefore, how to conduct scientific and accurate operation and maintenance management of offshore wind farms to improve the efficiency of offshore operation and maintenance has become one of the current research centers.

[0003] Therefore, the present invention provides an offshore wind farm operation and maintenance management system. Summary of the invention

[0004] The present invention provides an offshore wind farm operation and maintenance management system, which is used to transmit the equipment operating parameters collected in real time to a target data platform; the target data platform identifies equipment abnormalities and generates maintenance suggestions for corresponding processing based on the received equipment operating parameters; the operation and maintenance personnel monitor the operating status and equipment maintenance status of the target equipment in real time, which can effectively improve the accuracy and scientificity of the operation and maintenance management of the offshore wind farm, thereby improving the efficiency of offshore operation and maintenance.

[0005] The present invention provides an offshore wind farm operation and maintenance management system, comprising:

[0006] Data collection and transmission module: used to collect the equipment operating parameters of all target devices in real time using pre-deployed IoT devices, and transmit them to the target data platform through wireless networks;

[0007] Abnormal identification module: used by the target data platform to identify abnormalities of equipment based on the received equipment operating parameters and obtain abnormal analysis results;

[0008] Intelligent decision-making module: used to generate corresponding maintenance suggestions and handle them according to the abnormal analysis results;

[0009] Remote monitoring module: used by operation and maintenance personnel to monitor the operating status of target equipment as well as abnormal and early warning maintenance in real time.

[0010] Preferably, the IoT device refers to a smart sensor deployed in the wind farm area.

[0011] Preferably, the abnormality identification module includes:

[0012] Data processing unit: used for the target data platform to perform data preprocessing on the received device operating parameters to obtain first operating parameters, and to mark the first operating parameters as target devices;

[0013] A threshold determination unit: used for analyzing and updating a set parameter threshold of a corresponding first operating parameter based on the maintenance status of the current target device;

[0014] Model adjustment unit: used to adjust the parameters of the pre-established abnormal warning model using the updated setting parameter threshold value if the setting parameter threshold value at the current moment is updated;

[0015] Abnormal identification unit: used to compare the first operating parameter with the corresponding set parameter threshold, and combine the abnormal warning model to perform abnormal identification and warning on the current target device, obtain the abnormal analysis result and output it.

[0016] Preferably, the abnormality identification unit comprises:

[0017] When a parameter value of a first operating parameter exceeds a corresponding set parameter threshold, marking the first operating parameter as an abnormal parameter, and determining that the corresponding target device is an abnormal device;

[0018] Acquire all first operating parameters of the abnormal device except the abnormal parameter, and compare them with corresponding set parameter thresholds to obtain parameter absolute differences;

[0019] If there is a first operating parameter whose absolute parameter difference is greater than the set parameter difference threshold, the corresponding first operating parameter is regarded as a possible abnormal parameter;

[0020] When the target device does not have a first operating parameter that exceeds the corresponding set parameter threshold, the target device is marked as an analysis device, and all corresponding first operating parameters of the analysis device are input into the abnormal warning model to output an abnormal warning result;

[0021] When there are possible abnormal parameters in the abnormal warning result, the analysis device is marked as a warning device;

[0022] When there are no possible abnormal parameters in the abnormal warning result, marking the analysis device as a normal device;

[0023] A report generating unit: used for generating a device abnormality report based on the abnormality parameters, abnormality occurrence time, abnormality possible parameters and abnormal devices;

[0024] Generate equipment warning reports based on abnormal warning results and warning equipment;

[0025] The device abnormality report or the device early warning report is output as an abnormality analysis result.

[0026] Preferably, the threshold determination unit includes:

[0027] According to the equipment maintenance record of the current target equipment, if the equipment usage time of the current target equipment does not exceed the set usage time period and there is no equipment maintenance record, the initial parameter threshold of the current target equipment is used as the set parameter threshold;

[0028] If the device usage time of the current target device does not exceed the set usage time period and there is a device maintenance record, obtaining the first maintenance-related parameter from the device maintenance record;

[0029] Extracting a setting parameter threshold of a first maintenance-related parameter of the target device at the current moment, adjusting it using a threshold adjustment coefficient calculated based on the currently acquired device maintenance record to obtain a first adjustment parameter threshold, and outputting it as the setting parameter threshold;

[0030] using an initial parameter threshold of a first operating parameter other than the first maintenance-related parameter of the current target device as a set parameter threshold;

[0031] If the device usage time of the current target device exceeds the set usage time period and there is no device maintenance record, then the absolute difference between the device usage time of the current target device and the first time of the set usage time period is calculated;

[0032] Using the first absolute time difference, the set parameter thresholds of all first operating parameters of the current target device at the current moment are adjusted to obtain a first threshold value, which is output as the set parameter threshold value;

[0033] If the device usage time of the current target device exceeds the set usage time period and there is a device maintenance record, then obtain the second maintenance-related parameter from the device maintenance record;

[0034] Extracting a setting parameter threshold of a second maintenance-related parameter of the target device at the current moment, adjusting it using a threshold adjustment coefficient calculated based on the currently acquired device maintenance record to obtain a second adjustment parameter threshold, and outputting it as the setting parameter threshold;

[0035] treating the first operating parameters of the current target device other than the second maintenance-related parameters as parameters to be adjusted;

[0036] Calculate the absolute difference between the device usage time of the current target device and the second time of the set usage time period;

[0037] The parameter threshold to be adjusted is adjusted using the second time absolute difference to obtain a second threshold, which is output as the setting parameter threshold.

[0038] Preferably, the calculation formula of the threshold adjustment coefficient is as follows:

[0039] In the formula, f i It is represented as the threshold adjustment coefficient for adjusting the set parameter threshold of the i-th maintenance-related parameter of the current target device at the current moment; T0 is represented as the device usage time of the target device at the current moment; T1 is represented as the set usage time period of the target device; α is represented as the influence weight of the device usage time on the calculation of the threshold adjustment coefficient; γ is represented as the influence weight of the correlation degree between the i-th maintenance-related parameter of the current target device and the device abnormality on the calculation of the threshold adjustment coefficient; w ij is the jth equipment maintenance evaluation index of the i-th maintenance-related parameter of the current target equipment, where j = 1, 2, ..., n; n is the total number of equipment maintenance evaluation indexes; ε j It is represented as the contribution weight of the jth equipment maintenance evaluation index to the evaluation of the correlation between maintenance-related parameters and equipment abnormality.

[0040] Preferably, the intelligent decision-making module,

[0041] Abnormal decision unit: used to input the equipment abnormality report in the abnormality analysis result into the pre-established abnormality suggestion model to obtain abnormality handling suggestions;

[0042] Combining the exception handling suggestion with the corresponding equipment exception report to generate an exception response report, and transmitting it to the exception maintenance personnel;

[0043] The abnormal maintenance personnel performs abnormal maintenance according to the received abnormal response report, and uploads the abnormal maintenance result to the target data center;

[0044] Early warning decision unit: used to input the equipment early warning report in the abnormal analysis results into the pre-established early warning suggestion model to obtain early warning processing suggestions;

[0045] Combining the warning processing suggestion with the corresponding equipment abnormality report to generate a warning response report, and transmitting it to the warning maintenance personnel;

[0046] The early warning maintenance personnel performs early warning maintenance according to the received early warning response report, and uploads the early warning maintenance result to the target data center.

[0047] Preferably, the remote monitoring module includes:

[0048] User login unit: used by operation and maintenance personnel to establish communication with the target data center using smart devices and independently select the authentication method to perform user authentication;

[0049] When the identity authentication is successful, the operation and maintenance personnel automatically log in to the device monitoring interface of the target data center;

[0050] Monitoring unit: It is used by operation and maintenance personnel to view the operating parameters of the target equipment, as well as abnormal and warning maintenance status in real time through the visual dashboard on the equipment monitoring interface.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] By transmitting the equipment operating parameters collected in real time to the target data platform; the target data platform identifies equipment anomalies and generates maintenance suggestions based on the received equipment operating parameters for corresponding processing; the operation and maintenance personnel monitor the operating status and equipment maintenance status of the target equipment in real time, which can effectively improve the accuracy and scientificity of offshore wind farm operation and maintenance management, thereby improving the efficiency of offshore operation and maintenance.

[0053] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0054] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0056] Figure 1 This is a structural diagram of an offshore wind farm operation and maintenance management system in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0058] The embodiment of the present invention provides an offshore wind farm operation and maintenance management system, such as Figure 1 As shown, including:

[0059] Data collection and transmission module: used to collect the equipment operating parameters of all target devices in real time using pre-deployed IoT devices, and transmit them to the target data platform through wireless networks;

[0060] Abnormal identification module: used by the target data platform to identify abnormalities of equipment based on the received equipment operating parameters and obtain abnormal analysis results;

[0061] Intelligent decision-making module: used to generate corresponding maintenance suggestions and handle them according to the abnormal analysis results;

[0062] Remote monitoring module: used by operation and maintenance personnel to monitor the operating status of target equipment as well as abnormal and early warning maintenance in real time.

[0063] In this embodiment, the Internet of Things device refers to the intelligent sensor deployed in the wind farm area, such as wind speed sensors, wind direction sensors, and vibration monitors; the target device refers to the equipment in the wind farm area, such as wind rotors, generators, and substations; the equipment operating parameters refer to the data of the target equipment operation, such as wind speed, wind direction, current, voltage, etc.; the target data platform refers to a cloud platform that stores, manages, and analyzes a large amount of real-time data; the abnormality identification result refers to the equipment abnormality report or the equipment early warning report; the maintenance suggestions include abnormal maintenance suggestions and early warning maintenance suggestions.

[0064] The beneficial effects of the above technical solution are: by transmitting the equipment operating parameters collected in real time to the target data platform; the target data platform identifies equipment anomalies and generates maintenance suggestions for corresponding processing based on the received equipment operating parameters; the operation and maintenance personnel monitor the operating status and equipment maintenance status of the target equipment in real time, which can effectively improve the accuracy and scientificity of the operation and maintenance management of offshore wind farms, thereby improving the efficiency of offshore operation and maintenance.

[0065] An embodiment of the present invention provides an offshore wind farm operation and maintenance management system, wherein the abnormality identification module comprises:

[0066] Data processing unit: used for the target data platform to perform data preprocessing on the received device operating parameters to obtain first operating parameters, and to mark the first operating parameters as target devices;

[0067] A threshold determination unit: used for analyzing and updating a set parameter threshold of a corresponding first operating parameter based on the maintenance status of the current target device;

[0068] Model adjustment unit: used to adjust the parameters of the pre-established abnormal warning model using the updated setting parameter threshold value if the setting parameter threshold value at the current moment is updated;

[0069] Abnormal identification unit: used to compare the first operating parameter with the corresponding set parameter threshold, and combine the abnormal warning model to perform abnormal identification and warning on the current target device, obtain the abnormal analysis result and output it.

[0070] In this embodiment, data preprocessing refers to data cleaning and data normalization; the first operating parameter refers to the data obtained after data preprocessing of the received equipment operating parameters; the setting parameter threshold is obtained after analysis and adjustment based on the equipment maintenance situation; the abnormal warning model refers to the model obtained by collecting the operating parameter data of all target equipment and preprocessing and extracting equipment abnormality-related features to establish a training data set, using the training data set and the initial parameter threshold as input to train the neural network, which is used to identify operating parameters that may have abnormalities in the future and the time when the abnormality is predicted to occur; the abnormal analysis result refers to the equipment abnormality report and the equipment warning report.

[0071] The beneficial effect of the above technical solution is: the received equipment operating parameters are preprocessed through the target data platform to obtain the first operating parameters, and compared with the dynamically updated set parameter thresholds, abnormalities are identified and warned for the current target equipment to obtain abnormal analysis results, which can provide effective data basis for subsequent intelligent decision-making, help to carry out timely maintenance and processing of abnormal equipment, and improve operation and maintenance safety.

[0072] An embodiment of the present invention provides an offshore wind farm operation and maintenance management system, wherein the abnormality identification unit comprises:

[0073] When a parameter value of a first operating parameter exceeds a corresponding set parameter threshold, marking the first operating parameter as an abnormal parameter, and determining that the corresponding target device is an abnormal device;

[0074] Acquire all first operating parameters of the abnormal device except the abnormal parameter, and compare them with corresponding set parameter thresholds to obtain parameter absolute differences;

[0075] If there is a first operating parameter whose absolute parameter difference is greater than the set parameter difference threshold, the corresponding first operating parameter is regarded as a possible abnormal parameter;

[0076] When the target device does not have a first operating parameter that exceeds the corresponding set parameter threshold, the target device is marked as an analysis device, and all corresponding first operating parameters of the analysis device are input into the abnormal warning model to output an abnormal warning result;

[0077] When there are possible abnormal parameters in the abnormal warning result, the analysis device is marked as a warning device;

[0078] When there are no possible abnormal parameters in the abnormal warning result, marking the analysis device as a normal device;

[0079] A report generating unit: used for generating a device abnormality report based on the abnormality parameters, abnormality occurrence time, abnormality possible parameters and abnormal devices;

[0080] Generate equipment warning reports based on abnormal warning results and warning equipment;

[0081] The device abnormality report or the device early warning report is output as an abnormality analysis result.

[0082] In this embodiment, an abnormal parameter refers to the first operating parameter whose parameter value exceeds the corresponding set parameter threshold; an abnormal device refers to a target device with abnormal parameters; a parameter absolute difference refers to the absolute value of the parameter value of the first operating parameter minus the corresponding set parameter threshold; an abnormal possible parameter refers to the first operating parameter whose parameter value does not exceed the corresponding set parameter threshold and whose parameter absolute difference is greater than the set parameter difference threshold; and the set parameter difference threshold refers to 15% of the set parameter threshold.

[0083] In this embodiment, the analysis device refers to a target device that does not have a first operating parameter that exceeds the corresponding set parameter threshold; the abnormal warning result refers to the result of inputting all the first operating parameters of the analysis device into the abnormal warning model output, such as the time when the abnormality is predicted to occur and the possible abnormal parameters; the warning device refers to the analysis device that has possible abnormal parameters in the abnormal warning result; the normal device refers to the analysis device that does not have possible abnormal parameters in the abnormal warning result; the device abnormality report is composed of abnormal parameters, the time when the abnormal parameters occur, the possible abnormal parameters and the basic equipment information of the abnormal device, wherein the basic equipment information refers to the equipment name, equipment model, equipment number and installation location; the equipment warning report is composed of the abnormal warning result and the basic equipment information of the warning device.

[0084] The beneficial effects of the above technical solution are: through accurate abnormality identification and warning of target equipment and corresponding abnormality and warning report generation and output, the operation and maintenance efficiency is significantly improved, the operation and maintenance cost is reduced, and the intelligence level of equipment management is enhanced.

[0085] An embodiment of the present invention provides an offshore wind farm operation and maintenance management system, wherein the threshold determination unit comprises:

[0086] According to the equipment maintenance record of the current target equipment, if the equipment usage time of the current target equipment does not exceed the set usage time period and there is no equipment maintenance record, the initial parameter threshold of the current target equipment is used as the set parameter threshold;

[0087] If the device usage time of the current target device does not exceed the set usage time period and there is a device maintenance record, obtaining the first maintenance-related parameter from the device maintenance record;

[0088] Extracting a setting parameter threshold of a first maintenance-related parameter of the target device at the current moment, adjusting it using a threshold adjustment coefficient calculated based on the currently acquired device maintenance record to obtain a first adjustment parameter threshold, and outputting it as the setting parameter threshold;

[0089] using an initial parameter threshold of a first operating parameter other than the first maintenance-related parameter of the current target device as a set parameter threshold;

[0090] If the device usage time of the current target device exceeds the set usage time period and there is no device maintenance record, then the absolute difference between the device usage time of the current target device and the first time of the set usage time period is calculated;

[0091] Using the first absolute time difference, the set parameter thresholds of all first operating parameters of the current target device at the current moment are adjusted to obtain a first threshold value, which is output as the set parameter threshold value;

[0092] If the device usage time of the current target device exceeds the set usage time period and there is a device maintenance record, then obtain the second maintenance-related parameter from the device maintenance record;

[0093] Extracting a setting parameter threshold of a second maintenance-related parameter of the target device at the current moment, adjusting it using a threshold adjustment coefficient calculated based on the currently acquired device maintenance record to obtain a second adjustment parameter threshold, and outputting it as the setting parameter threshold;

[0094] treating the first operating parameters of the current target device other than the second maintenance-related parameters as parameters to be adjusted;

[0095] Calculate the absolute difference between the device usage time of the current target device and the second time of the set usage time period;

[0096] The parameter threshold to be adjusted is adjusted using the second time absolute difference to obtain a second threshold, which is output as the setting parameter threshold.

[0097] In this embodiment, the equipment maintenance record is composed of equipment maintenance records, equipment maintenance records and equipment parts replacement records; the set usage time period is predetermined, generally 1 month; the first maintenance-related parameter refers to the parameter directly related to equipment failure or maintenance recorded in the existing equipment maintenance record when the equipment usage time of the target equipment does not exceed the set usage time period, such as wind speed and voltage; the threshold adjustment coefficient is used to adjust the set parameter threshold; the first adjustment parameter threshold refers to the value obtained by adjusting the set parameter threshold of the first maintenance-related parameter of the target equipment at the current moment using the threshold adjustment coefficient. For example, if the set parameter threshold of the first maintenance-related parameter at the current moment is x1, then the corresponding first adjustment parameter threshold is equal to Wherein, e represents the natural base, and f1 represents the currently obtained threshold adjustment coefficient.

[0098] In this embodiment, the first time absolute difference refers to the absolute difference between the device usage time and the set usage time period when the device usage time of the current target device exceeds the set usage time period and there is no device maintenance record; the first threshold refers to the value obtained by adjusting the set parameter thresholds of all first operating parameters at the current moment using the first time absolute difference when the device usage time of the target device exceeds the set usage time period and there is no device maintenance record; for example, if the device usage time of the target device 1 exceeds the set usage time period and there is no device maintenance record, the set parameter threshold L1 of the first operating parameter 1 of the target device 1 at the current moment is adjusted using the first time absolute difference a1, and the first threshold of the current first operating parameter 1 is equal to Among them, e represents the natural base.

[0099] In this embodiment, the second maintenance-related parameter refers to the parameter directly related to the equipment failure or maintenance recorded in the existing equipment maintenance record when the equipment usage time of the target equipment exceeds the set usage time period; the second adjustment parameter threshold refers to the value obtained by adjusting the set parameter threshold of the second maintenance-related parameter of the target equipment at the current moment using the threshold adjustment coefficient; the parameter to be adjusted refers to the first operating parameter other than the second maintenance-related parameter when the equipment usage time of the target equipment exceeds the set usage time period and there is an equipment maintenance record; the second absolute time difference refers to the absolute difference between the equipment usage time and the set usage time period when the equipment usage time of the current target equipment exceeds the set usage time period and there is an equipment maintenance record.

[0100] The beneficial effect of the above technical solution is that by dynamically adjusting the setting parameter threshold, the parameter threshold can be made more in line with the actual situation of the equipment, thereby improving the accuracy and reliability of anomaly detection, thereby helping to improve operation and maintenance efficiency and reduce operation and maintenance costs.

[0101] An embodiment of the present invention provides an offshore wind farm operation and maintenance management system, and the calculation formula of the threshold adjustment coefficient is as follows:

[0102] In the formula, f i It is represented as the threshold adjustment coefficient for adjusting the set parameter threshold of the i-th maintenance-related parameter of the current target device at the current moment; T0 is represented as the device usage time of the target device at the current moment; T1 is represented as the set usage time period of the target device; α is represented as the influence weight of the device usage time on the calculation of the threshold adjustment coefficient; γ is represented as the influence weight of the correlation degree between the i-th maintenance-related parameter of the current target device and the device abnormality on the calculation of the threshold adjustment coefficient; w ijis the jth equipment maintenance evaluation index of the i-th maintenance-related parameter of the current target equipment, where j = 1, 2, ..., n; n is the total number of equipment maintenance evaluation indexes; ε j It is represented as the contribution weight of the jth equipment maintenance evaluation index to the evaluation of the correlation between maintenance-related parameters and equipment abnormality.

[0103] In this embodiment, the equipment maintenance evaluation index includes the average maintenance time related to the maintenance-related parameters in the equipment maintenance record, the time difference between the average maintenance time and the maximum maintenance time, the time difference between the average maintenance time and the minimum maintenance time, and the number of occurrences of the maintenance-related parameters; the contribution weight of the equipment maintenance evaluation index to the evaluation of the correlation between the maintenance-related parameters and the equipment abnormality is obtained by solving the matrix constructed after pairwise comparison and relative importance scoring using the hierarchical analysis method.

[0104] The beneficial effect of the above technical solution is that by calculating the threshold adjustment coefficient to dynamically update the set parameter threshold, the parameter threshold can be made more consistent with the actual situation of the device, thereby improving the accuracy and reliability of anomaly detection.

[0105] An embodiment of the present invention provides an offshore wind farm operation and maintenance management system, wherein the intelligent decision-making module comprises:

[0106] Abnormal decision unit: used to input the equipment abnormality report in the abnormality analysis result into the pre-established abnormality suggestion model to obtain abnormality handling suggestions;

[0107] Combining the exception handling suggestion with the corresponding equipment exception report to generate an exception response report, and transmitting it to the exception maintenance personnel;

[0108] The abnormal maintenance personnel performs abnormal maintenance according to the received abnormal response report, and uploads the abnormal maintenance result to the target data center;

[0109] Early warning decision unit: used to input the equipment early warning report in the abnormal analysis results into the pre-established early warning suggestion model to obtain early warning processing suggestions;

[0110] Combining the warning processing suggestion with the corresponding equipment abnormality report to generate a warning response report, and transmitting it to the warning maintenance personnel;

[0111] The early warning maintenance personnel performs early warning maintenance according to the received early warning response report, and uploads the early warning maintenance result to the target data center.

[0112] In this embodiment, the abnormal suggestion model is a model obtained by training a neural network using historical equipment abnormality parameters and corresponding preset abnormal handling measures as training data, and is used to generate handling suggestions for equipment abnormalities based on the information in the equipment abnormality report; the abnormal handling suggestions are abnormal handling measures obtained after inputting the equipment abnormality report into the abnormal suggestion model, including maintenance steps, suggestions for replacing parts, adjusting equipment parameters, etc.; the abnormal response report is composed of the abnormal handling suggestions and the corresponding equipment abnormality report; the abnormal maintenance personnel refers to the maintenance personnel who handle the equipment abnormality; the abnormal maintenance results include success and failure.

[0113] In this embodiment, the early warning suggestion model is a model obtained by training a neural network using historical equipment possible abnormal parameters and corresponding preset early warning processing measures as training data, and is used to generate early warning processing suggestions for the equipment based on the information in the equipment early warning report; the early warning processing suggestion is the early warning processing measure obtained after inputting the equipment early warning report into the early warning suggestion model, such as equipment parameter optimization; the early warning response report is composed of the early warning processing suggestion and the corresponding equipment abnormality report; the early warning maintenance personnel refers to the maintenance personnel who perform equipment early warning processing; the early warning maintenance results include success and failure.

[0114] The beneficial effect of the above technical solution is: by generating corresponding abnormality handling suggestions and warning handling suggestions based on equipment abnormality reports and warning reports, and transmitting them to corresponding maintenance personnel for processing, the efficiency of abnormality and warning processing as well as the reliability and safety of equipment can be effectively improved.

[0115] An embodiment of the present invention provides an offshore wind farm operation and maintenance management system, wherein the remote monitoring module comprises:

[0116] User login unit: used by operation and maintenance personnel to establish communication with the target data center using smart devices and independently select the authentication method to perform user authentication;

[0117] When the identity authentication is successful, the operation and maintenance personnel automatically log in to the device monitoring interface of the target data center;

[0118] Monitoring unit: It is used by operation and maintenance personnel to view the operating parameters of the target equipment, as well as abnormal and warning maintenance status in real time through the visual dashboard on the equipment monitoring interface.

[0119] In this embodiment, the operation and maintenance personnel refer to personnel who want to remotely monitor the operating status of the target device; the smart device refers to a portable smart mobile device, such as a mobile phone or a tablet; the identity authentication method includes three methods: password authentication, face recognition authentication, and fingerprint authentication; the device monitoring interface refers to the interface for monitoring the operating status of the target device that the operation and maintenance personnel see after logging into the target data center, and the interface includes various operating parameters of the target device, device abnormality reports, and device early warning reports; the visual dashboard usually displays the operating parameters of the target device in the form of graphics, charts, dashboards, etc., such as wind speed, power generation, equipment temperature, and abnormal maintenance conditions, among which the abnormal and early warning maintenance conditions include abnormal maintenance conditions and early warning maintenance conditions, among which the abnormal maintenance conditions refer to abnormal parameters, possible abnormal parameters, and abnormal maintenance results of executing abnormal processing suggestions that appear during the operation of the target device, that is, success or failure; the early warning maintenance condition refers to possible abnormal parameters that appear during the operation of the target device and the early warning maintenance results of executing early warning processing suggestions, that is, success or failure.

[0120] The beneficial effect of the above technical solution is that through the user remotely monitoring the operating status and abnormal maintenance of the target equipment, the operation and maintenance personnel can timely understand the operating status of the equipment, reduce labor costs and maintenance costs, and improve the operating efficiency of the overall system.

[0121] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An offshore wind farm operation and maintenance management system, characterized in that: include: Data collection and transmission module: used to collect the equipment operating parameters of all target devices in real time using pre-deployed IoT devices, and transmit them to the target data platform through wireless networks; Abnormal identification module: used by the target data platform to identify abnormalities of equipment based on the received equipment operating parameters and obtain abnormal analysis results; Intelligent decision-making module: used to generate corresponding maintenance suggestions and handle them according to the abnormal analysis results; Remote monitoring module: used by operation and maintenance personnel to monitor the operating status of target equipment as well as abnormal and early warning maintenance in real time.

2. An offshore wind farm operation and maintenance management system according to claim 1, characterized in that: IoT devices refer to smart sensors deployed in the wind farm area.

3. An offshore wind farm operation and maintenance management system according to claim 1, characterized in that: The abnormality identification module comprises: Data processing unit: used for the target data platform to perform data preprocessing on the received device operating parameters to obtain first operating parameters, and to mark the first operating parameters as target devices; A threshold determination unit: used for analyzing and updating a set parameter threshold of a corresponding first operating parameter based on the maintenance status of the current target device; Model adjustment unit: used to adjust the parameters of the pre-established abnormal warning model using the updated setting parameter threshold value if the setting parameter threshold value at the current moment is updated; Abnormal identification unit: used to compare the first operating parameter with the corresponding set parameter threshold, and combine the abnormal warning model to perform abnormal identification and warning on the current target device, obtain the abnormal analysis result and output it.

4. An offshore wind farm operation and maintenance management system according to claim 3, characterized in that: The abnormality identification unit comprises: When a parameter value of a first operating parameter exceeds a corresponding set parameter threshold, marking the first operating parameter as an abnormal parameter, and determining that the corresponding target device is an abnormal device; Acquire all first operating parameters of the abnormal device except the abnormal parameter, and compare them with corresponding set parameter thresholds to obtain parameter absolute differences; If there is a first operating parameter whose absolute parameter difference is greater than the set parameter difference threshold, the corresponding first operating parameter is regarded as a possible abnormal parameter; When the target device does not have a first operating parameter that exceeds the corresponding set parameter threshold, the target device is marked as an analysis device, and all corresponding first operating parameters of the analysis device are input into the abnormal warning model to output an abnormal warning result; When there are possible abnormal parameters in the abnormal warning result, the analysis device is marked as a warning device; When there are no possible abnormal parameters in the abnormal warning result, marking the analysis device as a normal device; A report generating unit: used for generating a device abnormality report based on the abnormality parameters, abnormality occurrence time, abnormality possible parameters and abnormal devices; Generate equipment warning reports based on abnormal warning results and warning equipment; The device abnormality report or the device early warning report is output as an abnormality analysis result.

5. An offshore wind farm operation and maintenance management system according to claim 3, characterized in that: The threshold determination unit comprises: According to the equipment maintenance record of the current target equipment, if the equipment usage time of the current target equipment does not exceed the set usage time period and there is no equipment maintenance record, the initial parameter threshold of the current target equipment is used as the set parameter threshold; If the device usage time of the current target device does not exceed the set usage time period and there is a device maintenance record, obtaining the first maintenance-related parameter from the device maintenance record; Extracting a setting parameter threshold of a first maintenance-related parameter of the target device at the current moment, adjusting it using a threshold adjustment coefficient calculated based on the currently acquired device maintenance record to obtain a first adjustment parameter threshold, and outputting it as the setting parameter threshold; using an initial parameter threshold of a first operating parameter other than the first maintenance-related parameter of the current target device as a set parameter threshold; If the device usage time of the current target device exceeds the set usage time period and there is no device maintenance record, then the absolute difference between the device usage time of the current target device and the first time of the set usage time period is calculated; Using the first absolute time difference, the set parameter thresholds of all first operating parameters of the current target device at the current moment are adjusted to obtain a first threshold value, which is output as the set parameter threshold value; If the device usage time of the current target device exceeds the set usage time period and there is a device maintenance record, then obtain the second maintenance-related parameter from the device maintenance record; Extracting a setting parameter threshold of a second maintenance-related parameter of the target device at the current moment, adjusting it using a threshold adjustment coefficient calculated based on the currently acquired device maintenance record to obtain a second adjustment parameter threshold, and outputting it as the setting parameter threshold; treating the first operating parameters of the current target device other than the second maintenance-related parameters as parameters to be adjusted; Calculate the absolute difference between the device usage time of the current target device and the second time of the set usage time period; The parameter threshold to be adjusted is adjusted using the second time absolute difference to obtain a second threshold, which is output as the setting parameter threshold.

6. An offshore wind farm operation and maintenance management system according to claim 5, characterized in that: The calculation formula of the threshold adjustment coefficient is as follows: In the formula, f i It is represented as the threshold adjustment coefficient for adjusting the set parameter threshold of the i-th maintenance-related parameter of the current target device at the current moment; T0 is represented as the device usage time of the target device at the current moment; T1 is represented as the set usage time period of the target device; α is represented as the influence weight of the device usage time on the calculation of the threshold adjustment coefficient; γ is represented as the influence weight of the correlation degree between the i-th maintenance-related parameter of the current target device and the device abnormality on the calculation of the threshold adjustment coefficient; w ij The jth equipment maintenance evaluation index is represented as the i-th maintenance-related parameter of the current target equipment, where j=1, 2, ..., n; n represents the total number of equipment maintenance evaluation indexes; ε j It is represented as the contribution weight of the jth equipment maintenance evaluation index to the evaluation of the correlation between maintenance-related parameters and equipment abnormality.

7. An offshore wind farm operation and maintenance management system according to claim 1, characterized in that: The intelligent decision-making module comprises: Abnormal decision unit: used to input the equipment abnormality report in the abnormality analysis result into the pre-established abnormality suggestion model to obtain abnormality handling suggestions; Combining the exception handling suggestion with the corresponding equipment exception report to generate an exception response report, and transmitting it to the exception maintenance personnel; The abnormal maintenance personnel performs abnormal maintenance according to the received abnormal response report, and uploads the abnormal maintenance result to the target data center; Early warning decision unit: used to input the equipment early warning report in the abnormal analysis results into the pre-established early warning suggestion model to obtain early warning processing suggestions; Combining the warning processing suggestion with the corresponding equipment abnormality report to generate a warning response report, and transmitting it to the warning maintenance personnel; The early warning maintenance personnel performs early warning maintenance according to the received early warning response report, and uploads the early warning maintenance result to the target data center.

8. An offshore wind farm operation and maintenance management system according to claim 1, characterized in that: The remote monitoring module comprises: User login unit: used by operation and maintenance personnel to establish communication with the target data center using smart devices and independently select the authentication method to perform user authentication; When the identity authentication is successful, the operation and maintenance personnel automatically log in to the device monitoring interface of the target data center; Monitoring unit: It is used by operation and maintenance personnel to view the operating parameters of the target equipment, as well as abnormal and warning maintenance status in real time through the visual dashboard on the equipment monitoring interface.

Images