An AI-based intelligent energy-saving control system and method for electromechanical equipment

Abstract

The present invention relates to the field of electromechanical equipment management and control, and specifically discloses an energy-saving intelligent management and control system and method for electromechanical equipment based on AI technology. The present invention analyzes the changing trend curves of various fault-related representations when various types of faults occur in motor equipment, constructs a prediction model, collects operating data, draws changing trend curves of various representations, compares and determines fault hazards, obtains each predicted type of fault, and analyzes the estimated time point and estimated severity of the predicted type of fault. Before the fault actually occurs, the type, time and severity of problems that may occur in the motor equipment are predicted. Through multi-dimensional representation analysis, dynamic trend modeling and intelligent decision feedback, accurate prediction of fault hazards and energy-saving optimization are achieved. It solves the problems of fault troubleshooting omissions, insufficient evaluation reliability, and rigid maintenance plans in the existing technology, thereby providing technical support for efficient, safe and energy-saving operation of industrial equipment.

Description

Technical Field

[0001] The present invention relates to the field of electromechanical equipment management and control, and in particular to an energy-saving intelligent management and control system and method for electromechanical equipment based on AI technology. Background Art

[0002] With the development of technology and the improvement of industrial automation, the role of electromechanical equipment as a power source in various industrial processes has become increasingly prominent. However, over the long term, electromechanical equipment is subject to wear, aging, contamination, and other issues. These issues can lead to performance degradation, reduced efficiency, and even equipment failure, impacting production continuity and safety.

[0003] With the continuous improvement of the level of industrial automation, the operating efficiency and reliability of electromechanical equipment, as the core power source in industrial production, directly affect production continuity and economic benefits. At present, enterprises generally adopt regular maintenance and experience-based fault detection methods. Although they can partially reduce the risk of equipment failure, they are difficult to cope with dynamic changes under complex working conditions. Existing technologies mostly rely on single parameter threshold alarms or manual experience judgments, and lack systematic analysis of the correlation characteristics of multiple types of faults, resulting in insufficient fault prediction accuracy and difficulty in achieving precise maintenance. In addition, traditional maintenance strategies are often based on fixed cycles, which can easily lead to excessive maintenance or delayed maintenance. Not only does it increase operation and maintenance costs, it may also cause unplanned downtime due to sudden failures, seriously affecting production safety and energy efficiency optimization.

[0004] Significant challenges remain in the areas of energy conservation and fault prediction for electromechanical equipment. On the one hand, the massive amount of data generated during equipment operation is not fully exploited, and the correlation between fault characteristics and energy efficiency indicators has not been effectively modeled, making it difficult to detect potential faults early. On the other hand, existing prediction models are mostly based on static historical data and cannot dynamically capture equipment degradation trends. Their ability to comprehensively assess fault type, occurrence time, and severity is limited. Especially in high-energy-consuming industrial scenarios, the coupled effect of equipment energy efficiency degradation and potential faults further increases the difficulty of operation and maintenance, necessitating an intelligent, systematic solution. Summary of the Invention

[0005] To address these issues, this paper proposes an AI-based intelligent energy-saving management and control system for electromechanical equipment. Through multi-dimensional characterization and analysis, dynamic trend modeling, and intelligent decision-making feedback, this system accurately predicts potential faults and optimizes energy conservation. This system addresses existing issues such as missed troubleshooting, insufficient assessment reliability, and rigid maintenance plans, thereby providing technical support for the efficient, safe, and energy-efficient operation of industrial equipment.

[0006] The energy-saving intelligent management and control system for electromechanical equipment specifically includes:

[0007] Model building module: used to analyze the fault-related characterization change trend curves based on the historical operating data of various electromechanical equipment with various types of faults, and to build prediction models for various types of faults of electromechanical equipment.

[0008] Correlation characterization monitoring module: used to collect the operating data of the target electromechanical equipment at its historical maintenance time points, filter the characterization values ​​associated with each type of fault, and draw the change trend curve of each characterization.

[0009] Fault type prediction module: used to determine whether the target electromechanical equipment has potential fault hazards based on the change trend curve and prediction model. If so, analyze and predict the type of fault.

[0010] Time analysis module: used to analyze the risk values ​​of various characteristics and analyze the estimated time point of the predicted type of failure based on the change trend curve.

[0011] Severity analysis module: used to analyze the estimated severity of the predicted type of fault based on the change trend curve.

[0012] Diagnostic feedback module: used to feed back the predicted type of failure, estimated time point and estimated severity to the operation and maintenance center for processing.

[0013] Compared with the existing technology, the AI-based intelligent energy-saving management and control system for electromechanical equipment described in the present invention has the following beneficial effects:

[0014] 1. This technology achieves accurate prediction of potential faults and energy-saving optimization through multi-dimensional characterization analysis, dynamic trend modeling, and intelligent decision-making feedback. It addresses existing issues such as missed troubleshooting, insufficient assessment reliability, and rigid maintenance plans, thereby providing technical support for the efficient, safe, and energy-efficient operation of industrial equipment.

[0015] 2. The present invention constructs a prediction model for various types of faults in electromechanical equipment by obtaining the changing trend curves of various characteristics associated with various types of faults in electromechanical equipment. Combined with the changing trend curves of various characteristics associated with various types of faults in the target electromechanical equipment, the target electromechanical equipment is checked for potential fault hazards. The electromechanical equipment is comprehensively checked based on various characteristics of various types of faults, thereby avoiding omissions in the inspection and being able to predict the occurrence of potential faults, thereby achieving early intervention, reducing unplanned downtime, extending equipment life, and improving production efficiency and safety.

[0016] 3. The present invention collects the operating data of the target electromechanical equipment at various historical maintenance time points, draws the change trend curves of various characteristics associated with various types of faults in the target electromechanical equipment, and compares them with the prediction models of various types of faults in the electromechanical equipment, so as to determine whether the target electromechanical equipment has potential fault hazards, which can improve the reliability and accuracy of the evaluation results.

[0017] 4. The present invention obtains each predicted type of fault of the target electromechanical equipment and the estimated time point and estimated severity of each predicted type of fault, and provides feedback, which is conducive to formulating predictive and targeted maintenance plans for electromechanical equipment, and is conducive to adjusting maintenance plans according to prediction results, avoiding unnecessary premature maintenance or failures caused by delayed maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a schematic diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] See also Figure 1 As shown, the present invention provides an energy-saving intelligent management and control system for electromechanical equipment based on AI technology, including: a model building module: used to analyze the various characterization change trend curves associated with the fault when the fault occurs based on the historical operation data of each electromechanical equipment that has various types of faults, and to construct a prediction model for various types of faults of the electromechanical equipment.

[0022] As a preferred solution, the model building module includes: extracting historical fault information of each electromechanical equipment stored in the database, obtaining various types of faults that have occurred in the history of each electromechanical equipment, sorting and classifying them, obtaining each electromechanical equipment that has occurred various types of faults, and further obtaining historical operation data of each electromechanical equipment that has occurred various types of faults.

[0023] It should be noted that there are many ways to classify the types of failures in electromechanical equipment.

[0024] In a specific embodiment, the types of failures of electromechanical equipment include, but are not limited to, electrical failures, mechanical failures, and control system failures.

[0025] The time points for each maintenance of electromechanical equipment are set according to preset principles. Based on the historical operating data of each electromechanical equipment that has various types of faults, the operating data of each electromechanical equipment that has various types of faults at various historical maintenance time points before the fault occurs are screened and recorded as the operating data of each electromechanical equipment that has various types of faults at various historical maintenance time points.

[0026] It should be noted that the time points for each maintenance of each electromechanical equipment are the same, for example, the time point for the first maintenance of each electromechanical equipment is three months later, and the time point for the second maintenance is six months later.

[0027] It should be noted that the time of occurrence of each electromechanical device with each type of fault is different, and thus the historical maintenance time points before the occurrence of each electromechanical device with each type of fault are different.

[0028] In a specific embodiment, the maintenance interval of the electromechanical equipment is set, and the time points of each maintenance of the electromechanical equipment are set according to the preset equal time interval principle. For example, if the maintenance interval of the electromechanical equipment is three months, the time points of each maintenance of the electromechanical equipment are further set.

[0029] In another specific embodiment, maintenance stages are set for electromechanical equipment, and maintenance intervals corresponding to each maintenance stage are set. During each maintenance stage, maintenance time points are set according to a preset equal time interval principle, thereby obtaining the maintenance time points for each electromechanical equipment maintenance. For example, if an electromechanical equipment has three maintenance stages: 1-3 years, 3-5 years, and over 5 years, and the maintenance intervals corresponding to the three maintenance stages are six months, three months, and one month, respectively, then the maintenance time points for each electromechanical equipment maintenance are further obtained.

[0030] In another specific embodiment, the operation data of each electromechanical device at each historical maintenance time point is obtained, and then the operation data of each electromechanical device with each type of fault at each historical maintenance time point is screened.

[0031] According to the historical operation data of each electromechanical device having each type of fault, the operation data of each electromechanical device having each type of fault at the time when the fault occurs is obtained.

[0032] As a preferred solution, the model building module process further includes: setting various representations associated with various types of faults in electromechanical equipment, and screening to obtain various representations associated with the faults of various electromechanical equipment that have various types of faults.

[0033] It should be noted that the various characterizations associated with various types of faults in electromechanical equipment are obtained based on historical experience.

[0034] In a specific embodiment, the various fault types of electromechanical equipment include electrical faults, mechanical faults and control system faults, among which the various characteristics associated with electrical faults include short-circuit current, insulation resistance, temperature, voltage fluctuation and frequency change, etc., the various characteristics associated with mechanical faults include bearing wear, rotor eccentricity, shaft bending degree, shaft crack length and vibration displacement, etc., and the various characteristics associated with control system faults include voltage, current and temperature, etc.

[0035] According to the operation data of each electromechanical equipment having various types of faults at its historical maintenance time points and fault occurrence time points, the numerical values ​​of various fault-related representations of each electromechanical equipment having various types of faults at its historical maintenance time points and fault occurrence time points are obtained.

[0036] The historical maintenance time points and failure time points are summarized to obtain each time point, and a coordinate system is established with the time point as the horizontal axis and the numerical value of the representation as the vertical axis. According to the numerical values ​​of the various fault-related representations of each electromechanical equipment that has various types of faults at its historical maintenance time points and failure time points, the corresponding data points are marked in the coordinate system. The mathematical model establishment method is used to draw the change trend curve of the various fault-related representations of each electromechanical equipment that has various types of faults when a fault occurs.

[0037] It should be noted that the changing trend curve of the fault correlation representation is an upward trend curve or a downward trend curve. For example, if the fault correlation representation is temperature, the changing trend curve of the fault correlation representation is an upward trend curve. If the fault correlation representation is efficiency, the changing trend curve of the fault correlation representation is a downward trend curve.

[0038] The changing trend curves of various fault-related representations of various electromechanical equipment when various types of faults occur are fitted to obtain the changing trend curves of various fault-related representations of various types of faults of electromechanical equipment when various types of faults occur, and a prediction model for various types of faults of electromechanical equipment is constructed.

[0039] It should be noted that the changing trend curves of the various fault-related representations of each electromechanical equipment when a fault occurs are fitted. The specific process is: according to the preset equal time interval principle, each marked time point is selected from the changing trend curves of the various fault-related representations of each electromechanical equipment when a fault occurs.

[0040] The corresponding values ​​of each representation associated with each type of fault at each marked time point in each electromechanical device where the fault occurs are obtained, and the average value is calculated to obtain the average value of each representation associated with each type of fault at each marked time point in the electromechanical device where the fault occurs.

[0041] A coordinate system is established with the marked time point as the horizontal axis and the average value of the representation as the vertical axis. According to the average value of each representation associated with each type of fault at each marked time point in the electromechanical equipment where the fault occurs, the corresponding data points are marked in the coordinate system. The mathematical model establishment method is used to draw the change trend curve of each representation associated with the fault when each type of fault occurs in the electromechanical equipment.

[0042] It should be noted that, when each electromechanical device having various types of faults fails, the selected marking time points in the change trend curves of the various fault-related representations are the same.

[0043] Correlation characterization monitoring module: used to collect the operating data of the target electromechanical equipment at its historical maintenance time points, filter the characterization values ​​associated with each type of fault, and draw the change trend curve of each characterization.

[0044] It should be noted that the method of drawing the changing trend curves of various characteristics associated with various types of faults in the target electromechanical equipment is based on the same principle as the method of drawing the changing trend curves of various characteristics associated with the faults of various electromechanical equipment when they fail.

[0045] Fault type prediction module: used to determine whether the target electromechanical equipment has potential fault hazards based on the change trend curve and prediction model. If so, analyze and predict the type of fault.

[0046] As a preferred solution, the fault type prediction module includes: according to the prediction model of each type of fault of the electromechanical equipment, obtaining the change trend curve of each characterization associated with the fault when the electromechanical equipment has each type of fault, and recording it as the reference change trend curve of each characterization associated with each type of fault of the electromechanical equipment.

[0047] Compare the change trend curves of each representation associated with each type of fault of the target electromechanical equipment with the reference change trend curves of each representation associated with each type of fault of the electromechanical equipment, and obtain the shape similarity between the change trend curves of each representation associated with each type of fault of the target electromechanical equipment and the reference change trend curve of its representation, which is recorded as , Indicates the The number of the fault type, , Indicates the The number of the item representation, .

[0048] By using the fuzzy function formula Get the probability coefficient of each type of failure of the target electromechanical equipment ,in represents the correction factor of the preset probability coefficient, represents a natural constant, Indicates the preset target electromechanical device Type of fault associated with The weight factor of the term representation, , Indicates the preset threshold for the similarity of the shape of the trend curve.

[0049] As a preferred solution, the fault type prediction module also includes: comparing the probability coefficient of each type of fault occurring in the target electromechanical equipment with a preset probability coefficient warning value; if the probability coefficient of each type of fault occurring in the target electromechanical equipment is less than the preset probability coefficient warning value, then the target electromechanical equipment does not have a potential fault hazard; otherwise, the target electromechanical equipment has a potential fault hazard; the fault type corresponding to the target electromechanical equipment having a probability coefficient greater than or equal to the preset probability coefficient warning value is recorded as the possible fault type of the target electromechanical equipment; and statistics on the various types of faults that may occur in the target electromechanical equipment are recorded as the various predicted types of faults of the target electromechanical equipment.

[0050] In this embodiment, the present invention constructs a prediction model for various types of faults in electromechanical equipment by obtaining the changing trend curves of various characteristics associated with various types of faults in electromechanical equipment. Combined with the changing trend curves of various characteristics associated with various types of faults in the target electromechanical equipment, the target electromechanical equipment is checked for potential fault hazards. The electromechanical equipment is comprehensively checked based on various characteristics of various types of faults, thereby avoiding omissions in the inspection and being able to predict the occurrence of potential faults, thereby achieving early intervention, reducing unplanned downtime, extending equipment life, and improving production efficiency and safety.

[0051] In this embodiment, the present invention collects the operating data of the target electromechanical equipment at its historical maintenance time points, draws the change trend curves of various representations associated with various types of faults in the target electromechanical equipment, and compares them with the prediction models of various types of faults of the electromechanical equipment, so as to determine whether the target electromechanical equipment has potential fault hazards, thereby improving the reliability and accuracy of the evaluation results.

[0052] Time analysis module: used to analyze the risk values ​​of various characteristics and analyze the estimated time point of the predicted type of failure based on the change trend curve.

[0053] As a preferred solution, the time analysis module includes: according to the values ​​of the various fault-related representations of each electromechanical device at the time of the failure of each type of fault, obtaining the corresponding values ​​of the various fault-related representations at the time of the failure of each electromechanical device, and further obtaining the average value and minimum value of the various fault-related representations at the time of the failure of the electromechanical device, which are recorded as .

[0054] By analyzing the formula Obtain the hazard values ​​of various characteristics associated with various types of faults in electromechanical equipment ,in Represents the weight factors of the preset average value and minimum value respectively, , Indicates the correction amount of the preset hazard value.

[0055] It should be noted that the correction amount representing the risk value is a value close to zero.

[0056] In another specific embodiment, the risk values ​​of various representations associated with various types of faults in electromechanical equipment are set according to preset principles.

[0057] As a preferred solution, the time analysis module further includes: screening the hazard values ​​of various representations associated with various types of faults in the target electromechanical equipment according to the hazard values ​​of various representations associated with various types of faults in the electromechanical equipment.

[0058] According to the changing trend curves of various representations associated with various types of faults of the target electromechanical equipment, the changing trend curves of various representations associated with various predicted types of faults of the target electromechanical equipment are screened, and combined with the dangerous values ​​of various representations associated with various predicted types of faults of the target electromechanical equipment, the time points corresponding to the changing trend curves of various representations associated with various predicted types of faults of the target electromechanical equipment when the representations reach their dangerous values ​​are obtained, and the earliest time points when the representations reach their dangerous values ​​in the changing trend curves of the representations associated with various predicted types of faults of the target electromechanical equipment are obtained, and recorded as the estimated time points when various predicted types of faults of the target electromechanical equipment occur.

[0059] In another specific embodiment, a mathematical analysis method is used to obtain a function corresponding to a change trend curve of each representation associated with each predicted type of failure of the target electromechanical equipment, and the hazard value of each representation associated with each predicted type of failure of the target electromechanical equipment is substituted to obtain an estimated time point when each predicted type of failure of the target electromechanical equipment occurs.

[0060] Severity analysis module: used to analyze the estimated severity of the predicted type of fault based on the change trend curve.

[0061] As a preferred solution, the degree analysis module includes: according to the prediction model of various types of faults of electromechanical equipment, obtaining the absolute value of the maximum tangent slope of each characterization change trend curve associated with each type of fault of the electromechanical equipment when the fault occurs, recording it as the predicted maximum tangent slope of each characterization change trend curve associated with each type of fault of the electromechanical equipment when the fault occurs, and screening the predicted maximum tangent slope of each characterization change trend curve associated with each predicted type of fault of the target electromechanical equipment.

[0062] According to the change trend curves of various representations associated with various predicted types of faults of the target electromechanical equipment, actual maximum tangent slopes of the change trend curves of various representations associated with various predicted types of faults of the target electromechanical equipment are obtained.

[0063] As a preferred solution, the degree analysis module further includes: obtaining the ratio between the actual maximum tangent slope of the change trend curve of each characterization associated with each predicted type of fault of the target electromechanical device and the predicted maximum tangent slope of the characterization change trend curve thereof, recording it as the relative tangent slope ratio of the change trend curve of each characterization associated with each predicted type of fault of the target electromechanical device, and expressing it as , Indicates the The number of predicted type failures, , The first The number of the item representation, .

[0064] As a preferred solution, the degree analysis module further includes: Get the estimated severity of each predicted type of failure of the target electromechanical equipment ,in A correction factor representing the preset estimated severity, Indicates the preset relative tangent slope ratio threshold, Indicates the first The weight factor of the term representation and .

[0065] Diagnostic feedback module: used to feed back the predicted type of failure, estimated time point and estimated severity to the operation and maintenance center for processing.

[0066] In this embodiment, the present invention obtains each predicted type of failure of the target electromechanical equipment and the estimated time point and estimated severity of each predicted type of failure, and provides feedback, which is conducive to formulating predictive and targeted maintenance plans for the electromechanical equipment, and is conducive to adjusting the maintenance plan according to the prediction results, avoiding unnecessary premature maintenance or failures caused by delayed maintenance.

[0067] In addition, the present invention also provides an AI-based intelligent energy-saving management and control method for electromechanical equipment, which specifically includes:

[0068] Step 1: Obtain historical operating data of each motor device that has various types of faults, analyze the changing trend curves of various fault-related characteristics of each motor device when the fault occurs, obtain the changing trend curves of various fault-related characteristics of each motor device when the fault occurs, and construct a prediction model for various types of faults of the motor device.

[0069] Step 2: Collect the operating data of the target motor equipment at each of its historical maintenance time points, filter the values ​​of various characteristics associated with various types of faults of the target motor equipment at each of its historical maintenance time points, and draw a trend curve of the various characteristics associated with various types of faults of the target motor equipment.

[0070] Step 3: Based on the trend curves of the various characteristics associated with various types of faults of the target motor equipment and the prediction models of various types of faults of the motor equipment, determine whether the target motor equipment has potential fault hazards. If so, analyze the various predicted types of faults of the target motor equipment.

[0071] Step 4: Analyze the risk values ​​of various characteristics associated with various types of faults in the motor equipment, and analyze the estimated time point of each predicted type of fault occurring in the target motor equipment based on the change trend curves of various characteristics associated with various types of faults in the target motor equipment.

[0072] Step 5: Analyze the estimated severity of each predicted type of fault occurring in the target motor device based on the change trend curves of each representation associated with each predicted type of fault of the target motor device.

[0073] Step 6: Feedback each predicted type of fault of the target motor equipment, the estimated time point and the estimated severity of each predicted type of fault of the target motor equipment to the operation and maintenance management center of the target motor equipment.

[0074] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0075] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0076] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0077] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0078] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0079] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An AI-based intelligent energy-saving management and control system for electromechanical equipment, characterized in that: include: Model building module: used to analyze the trend curves of various fault-related characteristics based on the historical operating data of various electromechanical equipment with various types of faults, and to build prediction models for various types of electromechanical equipment faults; Correlation characterization monitoring module: used to collect the operating data of the target electromechanical equipment at various historical maintenance time points, filter the characterization values ​​associated with each type of fault, and draw the change trend curve of each characterization; Fault type prediction module: used to determine whether the target electromechanical equipment has potential fault hazards based on the change trend curve and prediction model. If so, analyze and predict the type of fault. Time analysis module: used to analyze the risk value of each characteristic, and combine the change trend curve to analyze the estimated time point of the predicted type of failure; Severity analysis module: used to analyze the estimated severity of the predicted type of fault based on the change trend curve; Diagnosis feedback module: used to feed back the predicted fault type, estimated time point, and estimated severity to the operation and maintenance center for processing; The degree analysis module includes: According to the prediction model of each type of fault of the electromechanical equipment, the absolute value of the maximum tangent slope of the fault-related characterization change trend curve of each type of fault of the electromechanical equipment is obtained, and the absolute value is recorded as the predicted maximum tangent slope of the fault-related characterization change trend curve of each type of fault of the electromechanical equipment, and the predicted maximum tangent slope of the fault-related characterization change trend curve of each type of fault of the target electromechanical equipment is screened; Obtaining, according to the change trend curves of the various representations associated with the various predicted types of faults of the target electromechanical equipment, the actual maximum tangent slope of the change trend curves of the various representations associated with the various predicted types of faults of the target electromechanical equipment; The degree analysis module also includes: Obtaining the ratio of the actual maximum tangent slope of the change trend curve of each representation associated with each predicted type of fault of the target electromechanical device to the predicted maximum tangent slope of the change trend curve of the representation, and recording it as the relative tangent slope ratio of the change trend curve of each representation associated with each predicted type of fault of the target electromechanical device; The severity analysis module further includes: obtaining the estimated severity of each predicted type of failure occurring in the target electromechanical equipment by analyzing a multi-weight evaluation algorithm.

2. The AI-based intelligent energy-saving management and control system for electromechanical equipment according to claim 1 is characterized by: The model building module includes: Extracting historical fault information of each electromechanical device stored in the database, obtaining various types of faults that occurred in the history of each electromechanical device, sorting and classifying them, obtaining each electromechanical device that had each type of fault, and obtaining historical operating data of each electromechanical device that had each type of fault; Setting the time points for each maintenance of the electromechanical equipment according to a preset principle, and filtering the operating data of each electromechanical equipment with each type of fault at each historical maintenance time point before the fault occurs based on the historical operating data of each electromechanical equipment with each type of fault, and recording the data as the operating data of each electromechanical equipment with each type of fault at each historical maintenance time point; According to the historical operation data of each electromechanical device having each type of fault, the operation data of each electromechanical device having each type of fault at the time when the fault occurs is obtained.

3. The AI-based intelligent energy-saving management and control system for electromechanical equipment according to claim 2 is characterized by: The model building module also includes: Setting various representations associated with various types of faults of electromechanical equipment, and filtering out various representations associated with the faults of various types of electromechanical equipment; According to the operating data of each electromechanical device with each type of fault at each of its historical maintenance time points and the time point at which the fault occurred, the numerical values ​​of various fault-related representations of each electromechanical device with each type of fault at each of its historical maintenance time points and the time point at which the fault occurred are obtained; Summarize the historical maintenance time points and failure time points to obtain each time point, establish a coordinate system with the time point as the horizontal axis and the numerical value of the representation as the vertical axis, mark the corresponding data points in the coordinate system according to the numerical value of each fault-related representation of each electromechanical equipment at each historical maintenance time point and failure time point of each type of fault, and use the mathematical model establishment method to draw a change trend curve of each fault-related representation of each electromechanical equipment when a fault occurs; The changing trend curves of various fault-related representations of various electromechanical equipment when various types of faults occur are fitted to obtain the changing trend curves of various fault-related representations of various types of faults of electromechanical equipment when various types of faults occur, and a prediction model for various types of faults of electromechanical equipment is constructed.

4. The AI-based intelligent energy-saving management and control system for electromechanical equipment according to claim 1 is characterized by: The fault type prediction module includes: According to the prediction model of each type of electromechanical equipment fault, a change trend curve of each characteristic associated with each type of electromechanical equipment fault is obtained when each type of electromechanical equipment fault occurs, and the curve is recorded as a reference change trend curve of each characteristic associated with each type of electromechanical equipment fault; Comparing the change trend curves of each representation associated with each type of fault of the target electromechanical device with the reference change trend curves of each representation associated with each type of fault of the electromechanical device, and obtaining the shape similarity between the change trend curves of each representation associated with each type of fault of the target electromechanical device and the reference change trend curves of its representation; The probability coefficients of various types of failures in the target electromechanical equipment are obtained through fuzzy function analysis and calculation.

5. The AI-based intelligent energy-saving management and control system for electromechanical equipment according to claim 4 is characterized by: The fault type prediction module further includes: The probability coefficients of various types of failures occurring in the target electromechanical equipment are compared with the preset probability coefficient warning values. If the probability coefficients of various types of failures occurring in the target electromechanical equipment are all less than the preset probability coefficient warning values, then the target electromechanical equipment does not have any potential failure hazards. Otherwise, the target electromechanical equipment has potential failure hazards. The failure types corresponding to the target electromechanical equipment failure probability coefficients being greater than or equal to the preset probability coefficient warning values ​​are recorded as possible failure types of the target electromechanical equipment. The possible types of failures occurring in the target electromechanical equipment are counted and recorded as various predicted types of failures of the target electromechanical equipment.

6. The AI-based intelligent energy-saving management and control system for electromechanical equipment according to claim 3 is characterized by: The time analysis module includes: According to the values ​​of the various fault-related characteristics of each electromechanical device at the time of each fault, the corresponding values ​​of the various fault-related characteristics at the time of each electromechanical device fault are obtained. The average value and minimum value of the various fault-related characteristics at the time of each electromechanical device fault are further obtained, and they are recorded as ; By analyzing the formula Obtain the hazard values ​​of various characteristics associated with various types of faults in electromechanical equipment ,in Represents the weight factors of the preset average value and minimum value respectively, , Indicates the correction amount of the preset hazard value.

7. The AI-based intelligent energy-saving management and control system for electromechanical equipment according to claim 1 is characterized by: The time analysis module also includes: According to the hazard values ​​of various representations associated with various types of faults of the electromechanical equipment, the hazard values ​​of various representations associated with various predicted types of faults of the target electromechanical equipment are screened; According to the changing trend curves of various representations associated with various types of faults of the target electromechanical equipment, the changing trend curves of various representations associated with various predicted types of faults of the target electromechanical equipment are screened, and combined with the dangerous values ​​of various representations associated with various predicted types of faults of the target electromechanical equipment, the time points corresponding to the changing trend curves of various representations associated with various predicted types of faults of the target electromechanical equipment when the representations reach their dangerous values ​​are obtained, and the earliest time points when the representations reach their dangerous values ​​in the changing trend curves of the representations associated with various predicted types of faults of the target electromechanical equipment are obtained, and recorded as the estimated time points when various predicted types of faults of the target electromechanical equipment occur.

Images