Electromechanical equipment fault alarm rescue system

Abstract

The invention relates to the technical field of electromechanical equipment alarm and rescue, in particular to an electromechanical equipment fault alarm and rescue system which is arranged in parallel with an electromechanical equipment main control system at an electromechanical equipment control terminal, and the electromechanical equipment main control system and an electromechanical equipment emergency rescue system are switched through a trigger module. The electromechanical equipment emergency rescue system comprises a state prediction module which inputs collected electromechanical equipment operation data into a pre-constructed state prediction model to generate equipment state information; and the trigger module is used for switching the electromechanical equipment main control system and the electromechanical equipment emergency rescue system. According to the invention, the fault rescue system is arranged in parallel, so that when the electromechanical equipment breaks down, the electromechanical equipment main control system is paused, all current and previous preset internal instructions and external instructions of the electromechanical equipment main control system are invalid, and the situation that a panic user may generate irrational operation behaviors to cause a secondary safety accident is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of electromechanical equipment alarm and rescue, and in particular to an electromechanical equipment fault alarm and rescue system. Background Art

[0002] The publication number is CN114594335A, which discloses a mechanical and electrical equipment fault alarm system, including a start-up control module, a data monitoring module, a data analysis module, a data processing module, an alarm module, a text message module, a PLC extended load module, a display module, an oil pressure and temperature sensor module, a lifting speed sensor module, a voltage and current module, a vibration sensor module and a communication processing module. The output end of the start-up control module is connected to the input end of the data monitoring module, the output end of the data monitoring module is connected to the input end of the data analysis module, the output end of the data analysis module is connected to the input end of the data processing module, the output end of the data processing module is connected to the input end of the alarm module, the external electrical connection of the data processing module is connected to the PLC extended load module, and the signal output end of the data processing module is fixedly installed with a display module.

[0003] As mentioned in the above application, the existing electromechanical equipment operation system is a separate control system, which is equipped with an alarm trigger device to send out an alarm signal. When the equipment fails, the control system still maintains the operation state. At this time, the panicked user may produce irrational operating behaviors, such as emergency stop operation, or randomly pressing the operation button. This disordered command input not only cannot effectively respond to emergencies, but may cause logical confusion in the control system, leading to secondary safety accidents. Secondly, the existing fault handling mechanism has a data disconnection problem. The system only has basic remote alarm functions and lacks the ability to synchronously collect, identify and transmit key fault parameters and fault types, which makes it impossible for rescue personnel to obtain fault data before arriving at the scene. This information gap directly leads to the need for repeated fault diagnosis for on-site rescue, which seriously restricts the efficiency of emergency rescue. Summary of the Invention

[0004] In order to solve the above problems, the present invention provides a mechanical and electrical equipment failure alarm and rescue system.

[0005] The present invention adopts the following technical solution: an electromechanical equipment fault alarm and rescue system, which is arranged in parallel with the electromechanical equipment main control system at the electromechanical equipment control terminal, and switches between the electromechanical equipment main control system and the electromechanical equipment emergency rescue system through a trigger module. The electromechanical equipment emergency rescue system includes:

[0006] Data acquisition module, real-time collection of electromechanical equipment operation data;

[0007] The state prediction module inputs the collected electromechanical equipment operation data into the pre-built state prediction model to generate equipment state information;

[0008] The trigger module receives equipment status information or manual button commands to switch between the main control system of the electromechanical equipment and the emergency rescue system of the electromechanical equipment;

[0009] A brake control module obtains the motion state of the electromechanical device and generates a deceleration instruction based on the motion state of the electromechanical device;

[0010] Data processing module: obtains the operation data of the electromechanical equipment, generates the first fault characteristic parameter, and establishes the operation characteristic vector; obtains the state data of the car, generates the second fault characteristic parameter, and establishes the state characteristic vector; obtains the maintenance history statistical characteristics of the electromechanical equipment, generates the third fault characteristic parameter, and establishes the history characteristic vector;

[0011] The feature concatenation module concatenates the running feature vector, the state feature vector, and the historical feature vector into a long feature vector, performs dimensionality reduction processing on the long feature vector, removes redundant information, and obtains a low-dimensional vector Y;

[0012] The fault prediction module inputs the low-dimensional vector Y into the pre-built fault type prediction model to generate the fault type of the electromechanical equipment, and transmits the obtained low-dimensional vector Y and the fault type of the electromechanical equipment to the terminal PC to issue an alarm.

[0013] As a further description of the above technical solution: the electromechanical equipment operation data includes operation parameters and electrical parameters;

[0014] The operating parameters include the speed and acceleration of the electromechanical device during operation, and the operating parameters are obtained by using a MEMS accelerometer to collect acceleration data of the electromechanical device during startup, acceleration, constant speed, and deceleration, and obtaining speed and displacement information through integration processing;

[0015] The electrical parameters include voltage data and temperature data of the electromechanical equipment motor and brake. A voltage divider or an isolation amplifier is used to obtain the voltage data of the electromechanical equipment motor and brake, and an RTD sensor is used to monitor the temperature data of the electromechanical equipment motor and brake.

[0016] As a further description of the above technical solution: the method of obtaining the motion state of the electromechanical device and generating a speed reduction instruction based on the motion state of the electromechanical device includes:

[0017] When the device is still running, the encoder and magnetic sensor inside the device are used to obtain real-time position information to determine the position and direction of movement of the device;

[0018] Based on the direction of movement of the device, a "safe stop" target position is pre-set, and the remaining distance d between the current device position and the target position is calculated 剩 , obtain the device's braking distance ds based on the current speed and the device's maximum achievable deceleration;

[0019] If dleft < ds + Δ, where Δ is a preset safety margin, the distance from the electromechanical device to the next target position is obtained, a corrected braking distance is generated, and a deceleration command is generated based on the corrected braking distance and the operating speed of the electromechanical device;

[0020] If d 剩 ≥ds+Δ, based on d 剩 Generate a speed reduction instruction based on the operating speed of the electromechanical equipment.

[0021] As a further description of the above technical solution: the method of obtaining electromechanical equipment operation data, generating a first fault characteristic parameter, and establishing an operation characteristic vector includes:

[0022] Obtain the speed and acceleration of electromechanical equipment during operation, voltage data, temperature data, noise data, and vibration signals of the motor and brake of the electromechanical equipment, use low-pass and band-pass filters to remove high-frequency noise, and extract characteristic data;

[0023] Obtain the corresponding velocity average value, acceleration RMS value, voltage RMS value, temperature RMS value, noise data average value, and vibration signal RMS value through average value calculation and RMS value calculation;

[0024] An operation characteristic vector is established based on the characteristic data, and the operation characteristic vector is: {average value of velocity, root mean square value of acceleration, root mean square value of voltage, root mean square value of temperature, average value of noise data, root mean square value of vibration signal}.

[0025] As a further description of the above technical solution: the method of obtaining car state data, generating a second fault characteristic parameter, and establishing a state characteristic vector includes:

[0026] The acceleration sensor is used to collect vibration data of the elevator car; the sound sensor is used to monitor the noise data of the electromechanical equipment during operation, and low-pass and band-pass filters are used to remove high-frequency noise;

[0027] Each sensor uses a unified time reference to align all data with the same sampling frequency;

[0028] The corresponding vibration average value, vibration RMS value, noise average value and noise RMS value are obtained by average value calculation and RMS value calculation, and a state feature vector is established. The state feature vector is: {vibration average value, vibration RMS value, noise average value, noise RMS value}.

[0029] As a further description of the above technical solution: the method of obtaining the maintenance history statistical characteristics of the electromechanical equipment, generating the third fault characteristic parameter, and establishing the historical characteristic vector includes:

[0030] Obtain statistical characteristics of electromechanical equipment from maintenance history;

[0031] The statistical features include the fault frequency and the average time interval between consecutive maintenance events, as well as the total number of maintenance events, and the counting and calculation of the proportion of each type of fault;

[0032] The maintenance history statistical features are combined into a vector to establish a historical feature vector, wherein the historical feature vector is: {fault frequency, average time interval, total number of maintenance events, and proportion of each type of fault}.

[0033] As a further description of the above technical solution: the method of splicing the running feature vector, the state feature vector and the history feature vector into a long feature vector includes:

[0034] Z-score normalization is used for each element in the running feature vector, state feature vector, and historical feature vector to eliminate the dimension effect. Each time window of the running feature vector, state feature vector, and historical feature vector corresponds to a row of data. All features are arranged together in sequence and spliced into a long feature vector.

[0035] As a further description of the above technical solution: a method for performing dimensionality reduction processing on the feature long vector to eliminate redundant information includes:

[0036] The feature long vectors are combined into a data matrix X with a size of n×d, where n is the number of samples and d is the feature dimension. Each row of the data matrix X represents a time window and each column represents a feature. The mean μ is calculated for each column, and then the mean is subtracted from each data to make the data concentrate at 0 and normalize it.

[0037] Calculate the covariance matrix C of the data matrix X. The covariance matrix is calculated by subtracting the mean μ from each eigenvector column of the data matrix X to obtain the centering matrix Xnorm, and then transpose it to obtain Multiply with the original matrix and finally multiply by the scalar The calculation formula is: Where n is the number of samples, is the transposed matrix; Xnorm = X-μ, which is the value of each eigenvector in the update matrix minus the mean μ.

[0038] Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalue λi and the corresponding eigenvector wi;

[0039] The cumulative contribution rate threshold GX is preset, k features are selected based on the cumulative contribution rate threshold, and the dimension reduction transformation matrix P is constructed; the calculation formula of the cumulative contribution rate threshold GX is: Where d is the total number of characteristics and λi is the characteristic value;

[0040] The original data is projected into a new low-dimensional space to obtain the reduced-dimensional feature matrix Y, which is calculated as Y = Xnorm·P.

[0041] As a further description of the above technical solution: the training method of the state prediction model includes: obtaining the historical operating parameters of the electromechanical equipment of all electromechanical equipment in the area to which the electromechanical equipment belongs through the property database, the historical operating parameters of the electromechanical equipment include historical operating data and corresponding equipment status information, using the historical operating parameters of the electromechanical equipment as training data for the state prediction model, using the historical operating data as input, and using the corresponding equipment status information as output to form a training data pair; building a state prediction model, and training the state prediction model according to the training data.

[0042] As a further description of the above technical solution: the training method of the fault type prediction model includes:

[0043] Historical low-dimensional vectors Y and fault types are extracted from the property history database. Based on the historical low-dimensional vectors Y and fault types, a fault type prediction model is constructed using a generative adversarial network. The fault type of the electromechanical equipment is obtained based on the obtained low-dimensional vector Y and the trained fault type prediction model.

[0044] Beneficial effects:

[0045] In the above technical solution, the present invention provides an electromechanical equipment fault alarm and rescue system. By setting up a fault rescue system in parallel, when a fault occurs in the electromechanical equipment, the main control system of the electromechanical equipment can be suspended. All current and previously preset internal and external commands of the main control system of the electromechanical equipment will become invalid, thereby preventing panic users from making irrational operating behaviors, such as emergency stop operations or randomly pressing operating buttons. Such disordered command input not only fails to effectively respond to emergencies, but may also cause logical confusion in the control system, leading to secondary safety accidents such as abnormal movement of the electromechanical equipment or overload of the mechanical structure.

[0046] Furthermore, by preprocessing and feature extraction of data from various components of electromechanical equipment (such as motion data, electrical status, and maintenance history), a feature vector reflecting the real-time health status of the electromechanical equipment can be constructed. Multi-dimensional data fusion can capture tiny abnormal changes in equipment operation, predict potential faults in advance, and ensure that early warning information is accurate and timely, thereby greatly reducing the risk of accidents. By comprehensively utilizing the operating data and historical maintenance data of electromechanical equipment, and through layer-by-layer processing and fusion, a feature long vector that can reflect the operating health status of the electromechanical equipment is constructed, thereby improving the accuracy and timeliness of fault warning and emergency handling, and the obtained low-dimensional vector Y and the electromechanical equipment fault type are transmitted to the terminal PC to issue an alarm, so that rescue personnel can understand the fault parameters and fault type in real time, thereby improving rescue efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention will be further explained below in conjunction with the accompanying drawings and examples:

[0048] Figure 1 A module connection diagram of a mechanical and electrical equipment fault alarm and rescue system provided by an embodiment of the present invention;

[0049] Figure 2 A flow chart of a method for generating a speed reduction instruction based on the motion state of an electromechanical device provided in an embodiment of the present invention;

[0050] Figure 3 A flow chart of a method for establishing a historical feature vector provided by an embodiment of the present invention;

[0051] Figure 4 This is a flowchart of a method for performing dimensionality reduction processing on a long feature vector and eliminating redundant information provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the technical means, creative features, objectives and effects of the present invention easier to understand, the present invention is further described below with reference to specific diagrams. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless they conflict.

[0053] Example 1

[0054] See also Figure 1 , an embodiment of the present invention provides a technical solution: an electromechanical equipment fault alarm and rescue system, which is arranged in parallel with the electromechanical equipment main control system at the electromechanical equipment control terminal, and switches between the electromechanical equipment main control system and the electromechanical equipment emergency rescue system through a trigger module;

[0055] It should be noted that the main control system of electromechanical equipment is responsible for the normal operation of electromechanical equipment, including floor selection, speed control, door switch and electromechanical equipment overload alarm operations. The electromechanical equipment emergency rescue system has a higher priority than the main control system of electromechanical equipment to ensure that it can take over immediately when a fault occurs.

[0056] The electromechanical equipment emergency rescue system includes:

[0057] Data acquisition module, real-time collection of electromechanical equipment operation data;

[0058] Specifically, the electromechanical equipment operation data includes operation parameters and electrical parameters;

[0059] The operating parameters include the speed and acceleration of the electromechanical equipment during operation. The operating parameters use MEMS accelerometers to collect acceleration data of the electromechanical equipment during startup, acceleration, constant speed, and deceleration, and obtain speed and displacement information through integration processing. The MEMS accelerometer is installed in the car or shaft and does not affect the normal operation of the electromechanical equipment. It should be noted that abnormal acceleration curves or speed fluctuations may indicate problems with mechanical components (such as traction systems and braking systems).

[0060] The electrical parameters include voltage data and temperature data of the motor and brake of the electromechanical equipment, wherein a voltage divider or an isolation amplifier is used to obtain the voltage data of the motor and brake of the electromechanical equipment, and an RTD sensor is used to monitor the temperature data of the motor and brake of the electromechanical equipment; it should be noted that if the voltage or power fluctuates abnormally within a certain period of time, it may indicate a failure of the electrical components, and the temperature of key components (such as motors and brakes) may increase abnormally, which may be related to overload, poor heat dissipation or internal short circuit.

[0061] It should be noted that after the operation data of the electromechanical equipment is collected, it is transmitted to the state prediction module in real time through the signal conditioning module using communication interfaces such as RS485 and EtherCAT for state prediction.

[0062] A state prediction module inputs the collected electromechanical equipment operation data into a pre-built state prediction model to generate equipment state information, which includes normal state information and abnormal state information;

[0063] Specifically, the training method of the state prediction model includes: obtaining the historical operating parameters of the electromechanical equipment of all electromechanical equipment in the area to which the electromechanical equipment belongs through the property database, the historical operating parameters of the electromechanical equipment including historical operating data and corresponding equipment status information, using the historical operating parameters of the electromechanical equipment as training data for the state prediction model, using the historical operating data as input, and using the corresponding equipment status information as output to form a training data pair; building a state prediction model, and training the state prediction model according to the training data pair.

[0064] A trigger module receives device status information or manual button commands. When receiving abnormal status information or manual button commands, it generates a trigger command to control the electromechanical equipment to enter the rescue state and switch the electromechanical equipment main control system and the electromechanical equipment emergency rescue system;

[0065] It should be noted that when the electromechanical equipment switches to the electromechanical equipment emergency rescue system, the electromechanical equipment main control system is suspended, and all current and previously preset internal instructions and peripheral instructions of the electromechanical equipment main control system are invalid.

[0066] In this embodiment, by setting up a fault rescue system in parallel, the main control system of the electromechanical equipment can be suspended when a fault occurs in the electromechanical equipment, and all current and previously preset internal instructions and external instructions of the main control system of the electromechanical equipment will become invalid, so as to avoid irrational operating behaviors that may be made by panic users, such as emergency stop operations or random pressing of operation buttons. Such disordered command input not only cannot effectively respond to emergencies, but may cause logical confusion in the control system, leading to secondary safety accidents such as abnormal movement of electromechanical equipment or overload of mechanical structures.

[0067] Example: When the electromechanical equipment is an elevator;

[0068] The electromechanical equipment failure alarm and rescue system is arranged in parallel with the elevator main control system at the elevator control terminal, and the elevator main control system and the elevator emergency rescue system are switched through the trigger module;

[0069] It should be noted that the elevator main control system is responsible for the normal operation of the elevator, including floor selection, speed control, door switch and elevator overload alarm operations. The elevator emergency rescue system has a higher priority than the elevator main control system to ensure that it can take over immediately when a fault occurs.

[0070] The electromechanical equipment failure alarm and rescue system includes:

[0071] Data acquisition module, real-time collection of elevator operation data;

[0072] The collected elevator operation data is input into a pre-built fault prediction model to generate elevator status information, which includes normal status information and abnormal status information.

[0073] The trigger module receives elevator status information or manual button instructions. When it receives abnormal status information or manual button instructions, it generates a trigger instruction to control the elevator to enter the rescue state and switch the elevator main control system and the elevator emergency rescue system.

[0074] Example 2

[0075] See also Figure 1-Figure 2 , the embodiment of the present invention adds a brake control module on the basis of the above embodiment;

[0076] The brake control module obtains the motion state of the electromechanical device and generates a deceleration instruction based on the motion state of the electromechanical device;

[0077] The method of obtaining the motion state of the electromechanical device and generating a speed reduction instruction based on the motion state of the electromechanical device includes:

[0078] When the device is still running, the encoder and magnetic sensor inside the device are used to obtain real-time position information to determine the position and direction of movement of the device;

[0079] Based on the direction of movement of the device, a "safe stop" target position is pre-set, and the remaining distance d between the current device position and the target position is calculated 剩 , obtain the braking distance ds of the device based on the current speed and the maximum achievable deceleration of the device; where, a is the deceleration, which is a positive value and represents the magnitude of the braking force, and v is the operating speed of the electromechanical equipment.

[0080] If d 剩 <ds+Δ, where Δ is the preset safety margin; this indicates that the braking distance of the electromechanical equipment to the target position is insufficient. The distance from the electromechanical equipment to the next target position is obtained, and a corrected braking distance is generated. A deceleration command is generated based on the corrected braking distance and the operating speed of the electromechanical equipment.

[0081] If d 剩 ≥ds+Δ, it means that the braking distance of the electromechanical equipment to the target is sufficient, based on d 剩 Generate a speed reduction instruction based on the operating speed of the electromechanical equipment.

[0082] It's important to note that the safety margin Δ (D) is introduced primarily to compensate for uncertainties and delays in the control and execution processes, ensuring the equipment can safely stop. In actual operation, due to sensor noise, data acquisition delays, and control signal execution lags, the calculated ds may underestimate the actual required braking distance. Increasing Δ compensates for these errors, ensuring the equipment still has sufficient distance to come to a complete stop after braking is initiated.

[0083] The method for generating the speed reduction instruction is to use a PID (proportional-integral-differential) controller according to d 剩 The difference e between ds and ds is calculated to generate a deceleration command, so that the device can decelerate smoothly and stop at the target position accurately.

[0084] The formula for generating the speed reduction command based on the PID controller is:

[0085]

[0086] Where, u represents the generated deceleration (or deceleration) instruction, which controls the actuator to apply the corresponding braking force to the equipment. kp is the proportional coefficient, which is used to amplify e. ki is the integral coefficient, which is used to amplify the cumulative effect of the error over time. kd is the differential coefficient, which is used to amplify the error change rate and reflect the error trend. ∫edt represents the integral of e over a period of time. represents the derivative of e, that is, the rate of change of the error with time.

[0087] In this embodiment, by comparing the remaining distance in real time with the theoretical stopping distance plus a safety margin Δ, the system can initiate braking before the device is completely close to the target position, ensuring sufficient distance for smooth deceleration and preventing the device from "rushing out" of the predetermined safety zone due to braking delays. By using methods such as closed-loop PID control, the braking process is smoother, reducing the impact force on mechanical components and structures, thereby extending the service life of the equipment and reducing the risk of additional wear and failure caused by emergency stops.

[0088] Example 3

[0089] See also Figure 1-Figure 4 This embodiment adds a data processing module, a feature splicing module and a fault prediction module on the basis of the above embodiment.

[0090] Data processing module: obtains the operation data of the electromechanical equipment, generates the first fault characteristic parameter, and establishes the operation characteristic vector; obtains the state data of the car, generates the second fault characteristic parameter, and establishes the state characteristic vector; obtains the maintenance history statistical characteristics of the electromechanical equipment, generates the third fault characteristic parameter, and establishes the history characteristic vector;

[0091] The method of obtaining electromechanical equipment operation data, generating a first fault characteristic parameter, and establishing an operation characteristic vector includes:

[0092] Obtain the speed and acceleration of electromechanical equipment during operation, voltage data, temperature data, noise data, and vibration signals of the motor and brake of the electromechanical equipment, use low-pass and band-pass filters to remove high-frequency noise, and extract characteristic data;

[0093] Obtain the corresponding velocity average value, acceleration RMS value, voltage RMS value, temperature RMS value, noise data average value, and vibration signal RMS value through average value calculation and RMS value calculation;

[0094] An operation characteristic vector is established based on the characteristic data, and the operation characteristic vector is: {average value of velocity, root mean square value of acceleration, root mean square value of voltage, root mean square value of temperature, average value of noise data, root mean square value of vibration signal}.

[0095] The method of obtaining car state data, generating a second fault characteristic parameter, and establishing a state characteristic vector includes:

[0096] The acceleration sensor is used to collect vibration data of the elevator car; the sound sensor is used to monitor the noise data of the electromechanical equipment during operation, and low-pass and band-pass filters are used to remove high-frequency noise;

[0097] It should be noted that vibration energy or noise data that exceeds the normal baseline may indicate mechanical wear, guide misalignment, or loose components.

[0098] Each sensor uses a unified time reference to align all data with the same sampling frequency;

[0099] The corresponding vibration average value, vibration RMS value, noise average value and noise RMS value are obtained by average value calculation and RMS value calculation, and a state feature vector is established. The state feature vector is: {vibration average value, vibration RMS value, noise average value, noise RMS value}.

[0100] like Figure 3 As shown, the method of obtaining the maintenance history statistical characteristics of the electromechanical equipment, generating the third fault characteristic parameter, and establishing the historical characteristic vector includes:

[0101] Obtain statistical characteristics of electromechanical equipment from maintenance history;

[0102] The statistical features include the fault frequency and the average time interval between consecutive maintenance events, as well as the total number of maintenance events, and the counting and calculation of the proportion of each type of fault;

[0103] The maintenance history statistical features are combined into a vector to establish a historical feature vector, wherein the historical feature vector is: {fault frequency, average time interval, total number of maintenance events, and proportion of each type of fault}.

[0104] The feature splicing module splices the running feature vector, the state feature vector and the historical feature vector into a long feature vector, performs dimensionality reduction processing on the long feature vector, removes redundant information, and obtains a low-dimensional vector Y.

[0105] Methods for concatenating the running feature vector, the state feature vector, and the history feature vector into a long feature vector include:

[0106] Z-score standardization is used for each element in the operation feature vector, state feature vector, and historical feature vector to eliminate the dimension effect. Each time window of the operation feature vector, state feature vector, and historical feature vector corresponds to a row of data. All features are arranged together in order and spliced into a long feature vector. The long feature vector is expressed as: {average speed value, root mean square value of acceleration, root mean square value of voltage, root mean square value of temperature, average noise data, root mean square value of vibration signal, average vibration value, root mean square value of vibration, average noise value, root mean square value of noise, fault frequency, average time interval, total number of maintenance events, and proportion of each type of fault}.

[0107] Specifically, by preprocessing and feature extraction of data from various components of electromechanical equipment (such as motion data, electrical status, and maintenance history), a feature vector reflecting the real-time health status of the electromechanical equipment can be constructed. Multi-dimensional data fusion can capture tiny abnormal changes in equipment operation, predict potential failures in advance, and ensure that early warning information is accurate and timely, thereby greatly reducing the risk of accidents. By comprehensively utilizing the operating data and historical maintenance data of electromechanical equipment, and through layer-by-layer processing and fusion, a feature long vector that can reflect the operating health status of electromechanical equipment is constructed, thereby improving the accuracy and timeliness of fault warning and emergency response.

[0108] The method of performing dimensionality reduction processing on the feature long vector and removing redundant information includes:

[0109] The feature long vectors are combined into a data matrix X (size is n×d, where n is the number of samples and d is the feature dimension). Each row of the data matrix X represents a time window, and each column represents a feature. The mean μ is calculated for each column, and then the mean is subtracted from each data to make the data concentrate at 0 and normalize it.

[0110] Calculate the covariance matrix C of the data matrix X; the covariance matrix is calculated by subtracting the mean μ from each eigenvector column of the data matrix X to obtain the centralization matrix Xnorm, and then transpose it to obtain Multiply with the original matrix and finally multiply by the scalar The calculation formula is: Where n is the number of samples, is the transposed matrix of Xnorm; Xnorm = X-μ, which is the centralized matrix.

[0111] Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalue λi and the corresponding eigenvector wi;

[0112] Eigenvalue decomposition formula: Cwi = λiwi; It should be noted that the eigenvalue wi represents the amount of information contained in each eigenvector;

[0113] The cumulative contribution rate threshold GX is preset, k features are selected based on the cumulative contribution rate threshold, and the dimension reduction transformation matrix P is constructed; the calculation formula of the cumulative contribution rate threshold GX is: Where d is the total number of characteristics and λi is the characteristic value;

[0114] Project the original data into the new low-dimensional space to obtain the reduced-dimensional feature matrix Y, which is calculated as Y = Xnorm·P;

[0115] It should be noted that the low-dimensional vector Y of each time window can be regarded as a representation of the current health status of the electromechanical equipment.

[0116] Specifically, by compressing high-dimensional feature vectors into low-dimensional expressions, redundant information is removed while retaining the main variation information, thereby reducing the computational complexity and accelerating the response speed of the fault prediction module. The reduced-dimensional data is easier to process in real time, providing accurate and fast support for fault warning and improving the overall system security.

[0117] The fault prediction module inputs the low-dimensional vector Y into the pre-built fault type prediction model to generate the fault type of the electromechanical equipment, and transmits the obtained low-dimensional vector Y and the fault type of the electromechanical equipment to the terminal PC to issue an alarm.

[0118] Specifically, the training method of the fault type prediction model includes:

[0119] Historical low-dimensional vectors Y and fault types are extracted from the property history database. Based on the historical low-dimensional vectors Y and fault types, a fault type prediction model is constructed using a generative adversarial network. The fault type of the electromechanical equipment is obtained based on the obtained low-dimensional vector Y and the trained fault type prediction model.

[0120] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above-described embodiments. The above-described embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. An electromechanical equipment failure alarm and rescue system, characterized in that: It is set in parallel with the electromechanical equipment main control system at the electromechanical equipment control terminal, and switches between the electromechanical equipment main control system and the electromechanical equipment emergency rescue system through the trigger module. The electromechanical equipment emergency rescue system includes: Data acquisition module, real-time collection of electromechanical equipment operation data; The state prediction module inputs the collected electromechanical equipment operation data into the pre-built state prediction model to generate equipment state information; The trigger module receives equipment status information or manual button commands to switch between the main control system of the electromechanical equipment and the emergency rescue system of the electromechanical equipment; A brake control module obtains the motion state of the electromechanical device and generates a deceleration instruction based on the motion state of the electromechanical device; Data processing module: obtains the operation data of the electromechanical equipment, generates the first fault characteristic parameter, and establishes the operation characteristic vector; obtains the state data of the car, generates the second fault characteristic parameter, and establishes the state characteristic vector; obtains the maintenance history statistical characteristics of the electromechanical equipment, generates the third fault characteristic parameter, and establishes the history characteristic vector; The feature concatenation module concatenates the running feature vector, the state feature vector, and the historical feature vector into a long feature vector, performs dimensionality reduction processing on the long feature vector, removes redundant information, and obtains a low-dimensional vector Y; The fault prediction module inputs the low-dimensional vector Y into the pre-built fault type prediction model to generate the electromechanical equipment fault type, and transmits the obtained low-dimensional vector Y and the electromechanical equipment fault type to the terminal PC to issue an alarm.

2. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The electromechanical equipment operation data includes operation parameters and electrical parameters; The operating parameters include the speed and acceleration of the electromechanical device during operation, and the operating parameters are obtained by using a MEMS accelerometer to collect acceleration data of the electromechanical device during startup, acceleration, constant speed, and deceleration, and obtaining speed and displacement information through integration processing; The electrical parameters include voltage data and temperature data of the electromechanical equipment motor and brake. A voltage divider or an isolation amplifier is used to obtain the voltage data of the electromechanical equipment motor and brake, and an RTD sensor is used to monitor the temperature data of the electromechanical equipment motor and brake.

3. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The method of obtaining the motion state of the electromechanical device and generating a speed reduction instruction based on the motion state of the electromechanical device includes: When the device is still running, the encoder and magnetic sensor inside the device are used to obtain real-time position information to determine the device's position and direction of movement; Based on the direction of movement of the device, a "safe stop" target position is pre-set, and the remaining distance d between the current device position and the target position is calculated. 剩 , obtain the device's braking distance ds based on the current speed and the device's maximum achievable deceleration; If d 剩 <ds+Δ, where Δ is a preset safety margin. The distance from the electromechanical device to the next target position is obtained, and a corrected braking distance is generated. A deceleration command is generated based on the corrected braking distance and the operating speed of the electromechanical device. If d 剩 ≥ds+Δ, based on d 剩 Generate a speed reduction instruction based on the operating speed of the electromechanical equipment.

4. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The method of obtaining electromechanical equipment operation data, generating a first fault characteristic parameter, and establishing an operation characteristic vector includes: Obtain the speed and acceleration of electromechanical equipment during operation, voltage data, temperature data, noise data, and vibration signals of the motor and brake of the electromechanical equipment, use low-pass and band-pass filters to remove high-frequency noise, and extract characteristic data; Obtain the corresponding velocity average value, acceleration RMS value, voltage RMS value, temperature RMS value, noise data average value, and vibration signal RMS value through average value calculation and RMS value calculation; An operation characteristic vector is established based on the characteristic data, and the operation characteristic vector is: {average value of velocity, root mean square value of acceleration, root mean square value of voltage, root mean square value of temperature, average value of noise data, root mean square value of vibration signal}.

5. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The method of acquiring car state data, generating a second fault characteristic parameter, and establishing a state characteristic vector includes: The acceleration sensor is used to collect vibration data of the elevator car; the sound sensor is used to monitor the noise data of the electromechanical equipment during operation, and low-pass and band-pass filters are used to remove high-frequency noise; Each sensor uses a unified time reference to align all data with the same sampling frequency; The corresponding vibration average value, vibration RMS value, noise average value and noise RMS value are obtained by average value calculation and RMS value calculation, and a state feature vector is established. The state feature vector is: {vibration average value, vibration RMS value, noise average value, noise RMS value}.

6. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The method of obtaining the maintenance history statistical characteristics of the electromechanical equipment, generating the third fault characteristic parameter, and establishing the historical characteristic vector includes: Obtain statistical characteristics of electromechanical equipment from maintenance history; The statistical features include the fault frequency and the average time interval between consecutive maintenance events, as well as the total number of maintenance events, and the counting and calculation of the proportion of each type of fault; The maintenance history statistical features are combined into a vector to establish a historical feature vector, wherein the historical feature vector is: {fault frequency, average time interval, total number of maintenance events, and proportion of each type of fault}.

7. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The method of splicing the running feature vector, the state feature vector, and the history feature vector into a long feature vector includes: Z-score normalization is used for each element in the running feature vector, state feature vector, and historical feature vector to eliminate the dimension effect. Each time window of the running feature vector, state feature vector, and historical feature vector corresponds to a row of data. All features are arranged together in sequence and spliced into a long feature vector.

8. The electromechanical equipment failure alarm and rescue system according to claim 7, characterized in that: The method of performing dimensionality reduction processing on the feature long vector and removing redundant information includes: The feature long vectors are combined into a data matrix X with a size of n×d, where n is the number of samples and d is the feature dimension. Each row of the data matrix X represents a time window and each column represents a feature. The mean μ is calculated for each column, and then the mean is subtracted from each data to make the data concentrate at 0 and normalize it. Calculate the covariance matrix C of the data matrix X. The covariance matrix is calculated by subtracting the mean μ from each eigenvector column of the data matrix X to obtain the centering matrix Xnorm, and then transpose it to obtain Multiply with the original matrix and finally multiply by the scalar Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalue λi and the corresponding eigenvector wi; Preset the cumulative contribution rate threshold GX, select k features based on the cumulative contribution rate threshold, and construct the dimensionality reduction transformation matrix P; Project the original data into a new low-dimensional space to obtain the reduced-dimensional feature matrix Y.

9. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The training method of the state prediction model includes: obtaining the historical operating parameters of the electromechanical equipment of all electromechanical equipment in the area to which the electromechanical equipment belongs through the property database, the historical operating parameters of the electromechanical equipment including historical operating data and corresponding equipment status information, using the historical operating parameters of the electromechanical equipment as training data for the state prediction model, using the historical operating data as input, and using the corresponding equipment status information as output to form a training data pair; building a state prediction model, and training the state prediction model according to the training data.

10. The electromechanical equipment failure alarm and rescue system according to claim 1, characterized in that: The training method of the fault type prediction model includes: Historical low-dimensional vectors Y and fault types are extracted from the property history database. Based on the historical low-dimensional vectors Y and fault types, a fault type prediction model is constructed using a generative adversarial network. The fault type of the electromechanical equipment is obtained based on the obtained low-dimensional vector Y and the trained fault type prediction model.

Images