Intelligent detection system adaptive to safe operation of elevator

Abstract

The invention provides an intelligent detection system adaptive to safe operation of an elevator, and the system improves the accuracy of elevator fault detection and the accuracy of a response strategy. Firstly, a dynamic sensing module deploys a movable sensor array, and dynamic deployment is executed according to the running state and the stopping state of an elevator; thirdly, the intelligent analysis module constructs three independent evaluation dimensions of a physical analysis unit, a voiceprint analysis unit and a door system analysis unit, and three risk values are generated; and finally, implementing a differentiated three-level response mechanism by a grading execution module according to the three risk values, and respectively executing early warning monitoring, speed limiting maintenance and emergency stopping aiming at single abnormity, composite abnormity and door crack abnormity. Through cooperative work of dynamic sensing, multi-dimensional evaluation and graded response, the intelligent monitoring level and the active protection capacity of elevator safe operation are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of elevator operation, and particularly relates to an intelligent detection system adaptive to safe operation of an elevator. BACKGROUND

[0002] As an indispensable vertical transportation tool in modern buildings, the safe operation of an elevator is directly related to the safety of people's life and property. However, as a complex electromechanical system, the elevator inevitably has various faults and safety hazards in the long-term operation process. The traditional elevator safety detection mainly relies on artificial periodic inspection and annual mandatory inspection. However, the artificial inspection is limited by the experience level and subjective judgment of the detection personnel, and it is difficult to accurately identify early fault signs, and it is easy to miss detection and misjudgment. Moreover, the time interval of the periodic inspection is long, and the running state of the elevator cannot be grasped in real time, so that the fault hazards continue to accumulate within the inspection period, increasing the risk of sudden accidents.

[0003] An elevator intelligent detection system has appeared in the prior art. The system installs a vibration sensor in the elevator car, collects vibration data in the elevator operation process, and uses frequency spectrum analysis technology to identify abnormal vibration patterns, thereby realizing automatic detection of elevator mechanical faults. However, the prior art still has obvious deficiencies. First, the sensor deployment position is fixed and single, and it is impossible to adjust the monitoring focus according to different running states of the elevator. Second, the existing system often only focuses on single-dimensional fault features, and lacks fusion analysis of multi-source heterogeneous data. Finally, the prior art usually adopts a binary decision mode with a fixed threshold, that is, if the threshold is exceeded, an alarm is given, and if the threshold is not exceeded, it is normal. This one-size-fits-all approach cannot distinguish the severity of the fault, and it is also difficult to implement differentiated response strategies according to different fault types, which easily causes false alarms or missed alarms, affecting the practicality and reliability of the system. SUMMARY

[0004] In order to solve the technical problems mentioned in the background art, the present application proposes an intelligent detection system adaptive to safe operation of an elevator.

[0005] To this end, the technical solution adopted by the present application is as follows: An intelligent detection system adaptive to safe operation of an elevator, the system comprising: M1: a dynamic perception module, a movable sensor array is deployed inside the elevator shaft, the movable sensor array performs dynamic deployment according to the elevator state, and obtains a vibration spectrum diagram, a voiceprint feature matrix and a door gap width change curve of the elevator; M2: intelligent analysis module, including physical analysis unit, voiceprint analysis unit and door system analysis unit, the physical analysis unit identifies vibration mode and outputs first risk value through vibration spectrum and preset fault feature library; the voiceprint analysis unit analyzes voiceprint feature matrix, and obtains second risk value combined with cumulative running mileage of the elevator; the door system analysis unit obtains maximum value of door gap width and standard deviation of door gap width through door gap width change curve, and further outputs third risk value; M3: hierarchical execution module, implementing three-level response mechanism based on the first risk value, the second risk value and the third risk value.

[0006] Further, the movable sensor array includes a three-axis vibration sensor, an omnidirectional microphone and a radar sensor, The elevator state is divided into a running state and a stop state, and based on the running state and the stop state, the following deployments are respectively executed, 1) running state, the three-axis vibration sensor collects three-dimensional vibration signals of the elevator and transmits to the edge computing node, the edge computing node obtains vibration spectrum through wavelet transform and fast Fourier transform, and simultaneously performs normalization processing on the vibration spectrum; The omnidirectional microphone records acoustic signals of the elevator, and further obtains a voiceprint feature matrix through wavelet transform and short-time Fourier transform; 2) stop state, the radar sensor emits electromagnetic waves and receives reflected signals, measures the door gap width between the elevator door and the landing door by using the frequency-modulated continuous wave principle, and forms a door gap width change curve.

[0007] Further, the physical analysis unit processes the vibration spectrum through a convolutional neural network, and the convolutional neural network is trained through a preset fault feature library; The vibration spectrum is output to the trained convolutional neural network, and normal vibration probability value and abnormal vibration probability value are output, and the first risk value is calculated, which is represented as: Wherein, represents the first risk value; represents the abnormal vibration score; represents a positive number; when the normal vibration probability value is greater than the abnormal vibration probability value, the first risk value of the elevator is 0, and the elevator is in normal vibration mode; when the abnormal vibration probability value is greater than the normal vibration probability value, the first risk value is greater than 0, and the elevator is in abnormal vibration mode.

[0008] Further, the voiceprint analysis unit calculates the fundamental frequency according to the running speed of the elevator , which is represented as: Wherein, Indicates the spacing between guide rail joints; The voiceprint analysis unit extracts the fundamental frequency using a peak detection algorithm. The amplitudes of the harmonic components at integer multiples of frequency constitute the harmonic component vector of the audio waveform. And calculate the harmonic ratio, expressed as: in, Indicates the harmonic ratio; Indicates the fundamental frequency amplitude; Indicates the first The amplitude of each harmonic component; The guide rail wear index is calculated using the harmonic ratio and the elevator's cumulative operating mileage, and is expressed as follows: in, Indicates the guide rail wear index; Represents the regression coefficient; Indicates reference mileage; A wear threshold is set. If the guide rail wear index is not greater than the wear threshold, there is no second risk value. If the guide rail wear index is greater than the wear threshold, it is determined that abnormal guide rail wear has occurred, and a second risk value is calculated, expressed as: in, Indicates the second risk value; A score indicating the severity of guide rail wear; This indicates the wear threshold.

[0009] Furthermore, the maximum value of the door gap width is the maximum value among all sampling points on the door gap width variation curve; The standard deviation of the door gap width is a statistical measure of the dispersion of all data on the door gap width variation curve, expressed as: in, Indicates the standard deviation of the door gap width; Indicates the first The door gap width value corresponding to each sampling point; Indicates the number of sampling points; This represents the average width of the door gap; Combining the maximum door gap width and the standard deviation of the door gap width, the third risk value is calculated and expressed as: in, Indicates the third risk value; These represent the weighting coefficients for the maximum door gap width and the standard deviation of the door gap width, respectively. These represent reference values ​​for the maximum door gap width and the standard deviation of the door gap width, respectively. A threshold for abnormal door gaps is set. When the third risk value is greater than the preset threshold for abnormal door gaps, it is determined that an abnormal door gap width has occurred.

[0010] Further, the three-level response mechanism includes a first-level response mechanism, a second-level response mechanism, and a third-level response mechanism, The implementation condition of the first-level response mechanism is that the first risk value is greater than 0, or the second risk value exists; The implementation condition of the second-level response mechanism is that the first risk value is greater than 0, and the second risk value exists.

[0011] Further, the third-level response mechanism is the highest level of safety response, and the implementation condition is that the third risk value is greater than a preset door gap abnormal threshold.

[0012] Compared with the prior art, the advantages of the present application are: 1. The present application adopts a movable sensor array to perform dynamic deployment according to the running state and the stopping state of the elevator. In the running state, the sensor array is automatically gathered to the top of the car to form a dense detection network, accurately capturing vibration signals and acoustic signals. In the stopping state, the sensor array is dispersedly moved to the door area to monitor the door gap width in real time, realizing an intelligent monitoring mode of focusing on vibration and acoustic fingerprints during running and focusing on the door system during stopping, and significantly improving the pertinence of data acquisition and the capture ability of fault features.

[0013] 2. The present application constructs three independent risk assessment dimensions of physical analysis unit, acoustic fingerprint analysis unit and door system analysis unit, respectively outputs three risk values of vibration abnormality, guide rail wear abnormality and door gap width abnormality, overcomes the one-sidedness of single dimension detection in the prior art, comprehensively reflects the comprehensive health state of the elevator system, and effectively improves the accuracy and comprehensiveness of fault identification.

[0014] 3. The present application designs a differentiated three-level response mechanism, overcomes the extensive mode of fixed threshold binary determination in the prior art, realizes the implementation of precise response strategy according to the type and severity of abnormality, avoids the over-response caused by slight abnormality, ensures that the fault endangering life safety is strictly controlled, and significantly improves the practicability and reliability of the system. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Fig. 1 The intelligent detection flowchart of the present application; Fig. 2 The dynamic perception module flowchart of the present application; Fig. 3Flow chart of the intelligent analysis module of the present application. DETAILED DESCRIPTION

[0017] To achieve the above object, the present application is implemented by the following technical scheme, the present application provides an intelligent detection system suitable for safe operation of elevator, please refer to Figs. 1-3 The system comprises: M1: dynamic perception module, a movable sensor array is deployed inside the elevator shaft, the movable sensor array performs dynamic deployment according to the elevator state, and collects original data of the elevator, and obtains vibration spectrum, voiceprint feature matrix and door gap width change curve after processing, The module deploys a movable sensor array inside the elevator shaft, the sensor array comprises a plurality of sensor nodes, each sensor node is integrated with a three-axis vibration sensor, an omnidirectional microphone and a radar sensor, In this embodiment, the three-axis vibration sensor adopts a MEMS accelerometer, the measurement range is ± 16g, and the sampling frequency is set to 2000Hz, which is used to capture the vibration signal in the running process of the elevator; The frequency response range of the omnidirectional microphone is 20Hz to 20kHz, and the sampling rate is 44.1kHz, which is used to collect acoustic signals when the elevator is running; The working frequency of the radar sensor is 77GHz, the detection distance is 0.5 meters, and the distance resolution is 0.1 millimeter, which is used to monitor the door gap width between the layer door and the car door.

[0018] The movable sensor array performs dynamic deployment according to the elevator state, the elevator state is divided into running state and stopping state, In this embodiment, when the elevator enters the running state, the movable sensor array moves along the magnetic guide rail of the shaft through the built-in electric slide rail mechanism after receiving the elevator start signal, and is gathered to the monitoring area on the top of the elevator car. A dedicated sensor docking platform is arranged on the top of the car, and the movable sensor array is fixed on the platform by magnetic attraction to form a dense vibration and voiceprint joint detection network. At this time, the spatial distribution distance of the sensor nodes in the movable sensor array is reduced to 0.1 meters, which can accurately capture the local vibration signal and acoustic signal of the car in the running process, In the running phase, the three-axis vibration sensor collects three-dimensional vibration signals, and the three-dimensional vibration signals are transmitted to the edge computing node deployed on the shaft wall, and the edge computing node adopts an embedded processor; The edge computing node first performs noise reduction processing on the three-dimensional vibration signals by wavelet transform technology, then generates a vibration spectrum by fast Fourier transform on the three-dimensional vibration signals after noise reduction, and performs normalization processing on the vibration spectrum to map the amplitude to interval, In the running phase, the omnidirectional microphone synchronously records the acoustic signal, which is first subjected to wavelet denoising processing, and the same wavelet transform method as the vibration signal is adopted to obtain the denoised acoustic signal. In order to extract the voiceprint feature, the short-time Fourier transform is adopted to convert the denoised acoustic signal into a time-frequency domain representation, and a voiceprint feature matrix is formed according to the time-frequency domain representation. The rows of the matrix correspond to the time axis, the columns correspond to the frequency axis, and the numerical value of the matrix element represents the energy intensity of the frequency at the time; When the elevator enters the stopping state, that is, the elevator stops at a floor, the movable sensor array moves to the corresponding landing door area of the corresponding floor according to the car position information through the magnetic guide rail. In the landing door area, the radar sensor monitors the door gap width between the landing door and the elevator door in real time. Among them, the radar measures the door gap width by emitting electromagnetic waves and receiving reflected signals using the frequency-modulated continuous wave principle. The radar sensor continuously measures the door gap width at a frequency of 100 Hz to form a door gap width change curve. Under normal circumstances, the door gap width should be kept within the safety threshold.

[0019] M2: intelligent analysis module, including physical analysis unit, voiceprint analysis unit and door system analysis unit, the physical analysis unit identifies abnormal vibration mode by vibration spectrum and pre-set fault feature library and outputs first risk value; the voiceprint analysis unit analyzes the voiceprint feature matrix to obtain the voiceprint harmonic component, and obtains the second risk value in combination with the cumulative running mileage of the elevator; the door system analysis unit obtains the maximum value of the door gap width and the standard deviation of the door gap width through the door gap width change curve, and further outputs the third risk value, The physical analysis unit first adopts a convolutional neural network to perform pattern recognition on the vibration spectrum, and the convolutional neural network can automatically extract multi-level features in the vibration spectrum to realize accurate identification of abnormal vibration patterns, In this embodiment, the convolutional neural network includes three convolutional layers, two pooling layers, two fully connected layers and a Softmax classification layer. The input of the network is a vibration spectrum, which contains 2048 frequency points and a frequency range of 0 to 1000 Hz. Through layer-by-layer feature extraction of the three convolutional layers, the network can identify local pattern features in the vibration spectrum, such as peak values of specific frequencies, spectral envelope shapes, and combination relationships of multiple frequency components, to generate a feature map. The pooling layer reduces the dimension of the feature map while enhancing the translation invariance of the features, so that the network is robust to small frequency shifts. The fully connected layer maps the extracted features to two categories of normal vibration and abnormal vibration, The convolutional neural network is trained using a pre-set fault feature library. In this embodiment, the feature library contains 10,000 labeled samples, including all historical normal and abnormal vibration samples. The samples are derived from the historical operating data of the actual elevator and laboratory simulation data. The training process adopts a supervised learning approach, using the cross-entropy loss function to measure the difference between the prediction results and the true labels, and continuously optimizing the network parameters through the backpropagation algorithm. The vibration spectrum is input into the trained convolutional neural network, and finally, the normal vibration probability value is output through the Softmax classification layer. and abnormal vibration probability value The first risk value is further calculated and expressed as: in, To represent extremely small positive numbers, preventing the denominator from being 0; The abnormal vibration score is set according to the actual situation, so that the output of the first risk value is a score value. In this embodiment, the abnormal vibration score is set to 5. When the normal vibration probability value is greater than the abnormal vibration probability value, the max function outputs 0, and the elevator's first risk value is 0, indicating that the elevator is in normal vibration mode. Only when the abnormal vibration probability value is greater than the normal vibration probability value, that is, when the elevator is in abnormal vibration mode, will the first risk value be greater than 0.

[0020] The function of the acoustic signature analysis unit is to analyze the acoustic signature feature matrix, extract the acoustic signature harmonic components, calculate the guide rail wear index based on the elevator's cumulative operating mileage, and output a second risk value. During elevator operation, the friction between the guide rails and guide shoes generates periodic acoustic signals. The frequency characteristics of these signals are closely related to the elevator's speed and the condition of the guide rail surface. When the guide rail surface is smooth, the acoustic signals generated by friction are mainly concentrated on the fundamental frequency and its lower harmonic components. When the guide rail surface is worn, uneven, or locally damaged, the spectral composition of the friction noise becomes richer, and the energy of the higher harmonic components is significantly enhanced. The voiceprint analysis unit first determines the elevator's operating speed. Calculate the fundamental frequency , represented as: in, This indicates the spacing between the guide rail joints; in the acoustic signature feature matrix, besides the energy peak at the fundamental frequency, there are also harmonic components at integer multiples of the fundamental frequency. The acoustic signature analysis unit extracts the preceding harmonic components using a peak detection algorithm. The amplitude of the th harmonic component, specifically, for the th One harmonic component, in The maximum energy value in the range search is used as the first The amplitude of each harmonic component, For frequency tolerance, it is set to 5% of the fundamental frequency to accommodate small fluctuations in speed; Before extraction The amplitudes of each harmonic component constitute the harmonic component vector of the acoustic signature. To quantify the degree of guide rail wear, the acoustic signature analysis unit calculates the ratio of higher-order harmonic amplitudes to the fundamental frequency amplitude to obtain the harmonic ratio. , represented as: in, Indicates the fundamental frequency amplitude; Indicates the first The harmonic ratio reflects the energy proportion of high-frequency components relative to the fundamental frequency. When the guide rail surface is flat, the harmonic ratio is small, usually below 0.2. When the guide rail wear intensifies, the harmonic ratio increases significantly, reaching 0.8 or even higher. The harmonic ratio provides an intuitive acoustic characteristic parameter for guide rail condition assessment. However, harmonic ratio alone is insufficient to accurately predict guide rail wear, as guide rail wear is a long-term cumulative process closely related to the elevator's mileage. For example, a newly installed elevator may have a slightly higher harmonic ratio due to temporary factors during the installation and commissioning phase, and does not necessarily indicate that the guide rails are already worn. Conversely, an elevator that has been in operation for many years may have a slightly lower harmonic ratio, but due to accumulated wear, it may already be close to the replacement standard. Therefore, the acoustic analysis unit introduces the elevator's cumulative mileage as an auxiliary parameter. The cumulative mileage is obtained through an odometer and is expressed in kilometers, reflecting the elevator's total operating volume. Through harmonic ratio and cumulative operating mileage Based on the calculation of the guide rail wear index, it is expressed as: in, Indicates the guide rail wear index; Represents the regression coefficient; The reference operating mileage is set to 100 kilometers. The formula indicates that the guide rail wear index is jointly determined by acoustic characteristics (harmonic ratio) and usage history (cumulative operating mileage). The regression coefficients are determined through statistical analysis of a large amount of historical data. In this embodiment, a total of 500 sets of historical data were collected. Each set of data includes harmonic ratio, cumulative operating mileage, and actual measured guide rail surface roughness (measured by a surface roughness meter, in micrometers). The least squares method is used to perform multiple linear regression analysis to obtain the regression coefficients. The voiceprint analysis unit compares the guide rail wear index with a preset wear threshold. The wear threshold is the criterion for judging abnormal guide rail wear and is determined according to the guide rail's technical specifications and safety requirements. In this embodiment, the wear threshold is preset to 50. When the guide rail wear index is greater than 50, an abnormal guide rail wear is determined to have occurred, and a second risk value is calculated. When the guide rail wear index is not greater than 50, the second risk value is not output. The second risk value is calculated based on the guide rail wear index. The second risk value is expressed as a nonlinear function to reflect the nonlinear impact of wear on risk, as follows: wherein, represents the severity score of guide rail wear, which is set according to actual conditions, so that the output of the second risk value is a score value, and in the embodiment, the severity score of guide rail wear is set to 5; represents the wear threshold value; when increases, the exponential term gradually decreases, and the second risk value gradually increases; when is much larger than , the exponential term approaches 0, and the second risk value approaches the severity score, indicating that the risk reaches an extremely high level; this nonlinear relationship conforms to the actual law that guide rail wear has a smaller impact on safety, but when the wear reaches a certain degree, the safety risk will rise sharply.

[0021] The function of the door system analysis unit is to analyze the door gap width change curve, extract the maximum door gap width and the standard deviation of the door gap width, comprehensively evaluate the safety state of the door system, and output the third risk value, The door system is one of the most critical safety components of the elevator, and the door gap width is directly related to the personal safety of passengers. Under normal circumstances, when the elevator stops at a floor, the door gap width should be kept within the safety threshold value; if the door gap width is too large, it may be due to problems such as door guide rail deformation, door hanging wheel wear, and insufficient door machine torque, which is a fatal impact on the subsequent safe operation of the elevator. Therefore, the door system analysis unit takes the door gap width as the most priority monitoring index, The maximum door gap width is defined as the maximum value among all sampling points on the door gap width change curve, and in the embodiment, according to the elevator safety technical specification, the door gap width safety threshold value is set to 3 mm. The standard deviation of the door gap width is a statistical quantity that describes the degree of data dispersion, which is used to measure the fluctuation amplitude of the door gap width change curve, and is expressed as: wherein, represents the standard deviation of the door gap width; represents the door gap width value corresponding to the th sampling point; represents the number of sampling points; represents the mean value of the door gap width; the standard deviation of the door gap width reflects the stability of the door system; when the door system has mechanical faults, it will cause the elevator door to shake, stop or repeat, and the door gap width change curve will present irregular fluctuations, and the standard deviation will significantly increase, so the standard deviation of the door gap width is an important index for evaluating the health state of the door system.

[0022] After extracting the two key feature parameters, the door system analysis unit comprehensively calculates the third risk value by using the weighted summation method, and the calculation of the third risk value needs to consider both the absolute size and the fluctuation amplitude of the door gap width, and is expressed as: in, These represent reference values ​​for the maximum door gap width and the standard deviation of the door gap width, respectively, used for normalization processing; These represent the weighting coefficients for the maximum door gap width and the standard deviation of the door gap width, respectively. In this embodiment, the weighting coefficients are determined based on the severity analysis of door system failures and statistical analysis of a large amount of historical data. The allocation of these weighting coefficients reflects the contribution of characteristic parameters to safety risks. The maximum door gap width accounts for a larger proportion than the standard deviation of the door gap width. These reference values ​​are determined based on the technical specifications and safety standards of the elevator door system. The door system analysis unit compares the third risk value with the preset door gap anomaly threshold. When the third risk value is greater than the preset door gap anomaly threshold, it determines that an abnormal door gap width has occurred.

[0023] The tiered execution module implements a three-tiered response mechanism based on the first risk value, the second risk value, and the third risk value. This module serves as the execution terminal of the entire intelligent detection system. Based on the output of the intelligent analysis module, it implements a differentiated three-level response mechanism. The core of the three-level response mechanism is to implement a graded and classified response strategy according to the type, severity, and scope of safety impact of the anomaly, so as to ensure the safe operation of the elevator and avoid operational efficiency loss caused by over-response. The first-level response mechanism targets single-dimensional anomalies. Specifically, it is triggered when the first risk value is greater than 0, or a second risk value exists but the two do not occur simultaneously, and the third risk value does not exceed the door gap anomaly threshold, and no door gap width anomaly occurs; in this case, it is classified as a first-level risk state. From a risk perspective, both abnormal vibration and abnormal guide rail wear are progressive mechanical failures that will not immediately cause direct harm to passengers. However, if ignored for a long time, they may gradually evolve into serious malfunctions. Therefore, the strategy for a Level 1 response focuses on strengthening early warning and monitoring. When a Level 1 response is triggered, this module first records the anomaly information to the system database, including detailed information such as the time of occurrence, anomaly type, risk value, and elevator operating status, forming a complete fault tracing chain. Simultaneously, it automatically generates an early warning report, which is pushed in real-time to the maintenance management platform and the mobile terminals of property management personnel via IoT communication. The early warning report includes an anomaly description, preliminary cause analysis, and suggested inspection items. To closely monitor abnormal development trends, this module adjusts the operating mode of the dynamic sensing module, increasing the data acquisition frequency to several times the normal level. In this embodiment, the acquisition cycle of the triaxial vibration sensor and omnidirectional microphone is once every 30 minutes under normal conditions, and is shortened to once every 15 minutes after triggering the first-level response. In the first response state, the elevator continues to operate normally without limiting the running speed and service floors to maximize operational efficiency; the hierarchical execution module continuously monitors the subsequent collected risk value data, and if the risk value is normal in the next three collection periods, the first response state is automatically lifted and the normal monitoring mode is restored; if the risk value continues to exceed the threshold or shows an upward trend, the system remains in the first response state and prompts the property management personnel to arrange professional technicians to conduct on-site inspection and maintenance as soon as possible.

[0024] The second response mechanism is aimed at the situation of multi-dimensional abnormal superposition. The specific triggering condition is that when the first risk value is greater than 0 and there is a second risk value, i.e., vibration abnormality and guide rail wear abnormality occur at the same time, and the third risk value does not exceed the door gap abnormality threshold, i.e., no door gap width abnormality occurs, it is determined as a second risk state, From the fault mechanism analysis, the simultaneous occurrence of vibration abnormality and guide rail wear abnormality often means that the elevator mechanical system has a more serious composite fault, and the superposition of the two types of abnormalities can significantly enhance the destructive effect of each other; therefore, the focus of the second response mechanism is to reduce the operation risk and speed up the maintenance response, When the second response mechanism is triggered, the module first sends a speed limiting instruction to the elevator control system and increases the data collection frequency. In this embodiment, if the rated speed of the elevator is 2.5 meters per second, the maximum running speed after speed limiting is 1.5 meters per second; the speed limiting measure can effectively reduce the dynamic load and vibration amplitude of the mechanical system, slow down the fault deterioration speed, and at the same time provide a more stable riding experience for passengers, At the same time, the hierarchical execution module generates a second risk alarm information, which is sent to the maintenance management platform through the sound and light alarm device in the elevator car and the machine room, reminding passengers and maintenance personnel to pay attention to the elevator state, and automatically sending a high-priority repair work order, The hierarchical execution module continuously evaluates the effect of the second response mechanism, and if any of the first risk value and the second risk value exceeds the preset serious abnormality threshold after execution, it is automatically upgraded to the third response mechanism and executes more stringent safety measures.

[0025] The third response mechanism is the highest level of safety response, with the highest triggering priority. The specific triggering condition is that as long as the third risk value exceeds the door gap abnormality threshold, i.e., the door gap width abnormality occurs, regardless of whether the first risk value and the second risk value exist and are greater than 0, it is immediately determined as a third risk state and the emergency response program is started, The priority design of the third response mechanism is based on the special danger of the door system failure. The door gap width abnormality is directly related to the personal safety of passengers, and the accident often occurs suddenly and quickly, leaving a very short time window for response; therefore, the door gap width abnormality must be considered as the most urgent safety threat, triggering the most stringent protective measures, When the third level response mechanism is triggered, the module immediately sends an emergency stop command to the elevator control system; if the elevator is in operation, the safety stop program is started, first slowing down at normal deceleration, and stopping the elevator smoothly at the nearest floor, during the stopping process, if the door gap width is detected to be abnormally increased or other dangerous signals appear, the safety clamp or brake is triggered immediately to implement emergency stop; if the elevator is already in a stopped state, the control system prohibits the elevator from closing the door and starting again, and keeps the door open, After emergency stop, the hierarchical execution module issues a three-level risk warning through multiple channels, specifically, in the elevator car, a safety prompt is broadcast to passengers through the emergency intercom, informing them that the elevator has been suspended due to safety reasons, and asking them to remain calm and follow the instructions to safely leave; outside the elevator, a fault warning is issued through the LED display screen and the sound and light alarm to prevent other people from continuing to use the elevator; at the remote monitoring end, emergency alarm information is sent to the maintenance management platform, property management center and emergency management department simultaneously, and the emergency response plan is started, In the three-level response state, the elevator completely stops service and prohibits any operation, only after professional technicians complete comprehensive maintenance, confirm that the door system failure has been completely eliminated, the door gap width returns to the safe range, and multiple empty and loaded tests are verified qualified, the three-level response state can be authorized to be lifted and the elevator normal operation is restored.

[0026] The intelligent detection system adapted to the safe operation of the elevator proposed by the application realizes a complete closed loop from data collection, risk assessment to response execution through the collaborative work of the dynamic perception module, the intelligent analysis module and the hierarchical execution module. The dynamic perception module performs differential deployment according to the elevator running state and the stopping state. The intelligent analysis module constructs three independent risk assessment dimensions. The hierarchical execution module designs a differential three-level response mechanism, which implements early warning monitoring, speed limiting maintenance and emergency stop for single abnormality, composite abnormality and door gap abnormality respectively, ensuring the accuracy and effectiveness of the response strategy.

[0027] In summary, the application overcomes the shortcomings of fixed sensor position, single dimension detection and fixed threshold determination in the prior art through the organic combination of the dynamic deployment strategy of the movable sensor array, the multi-dimensional independent risk assessment system and the differential three-level response mechanism, realizes the comprehensive perception, accurate assessment and intelligent response of the elevator safety state, significantly improves the active protection capability, practicality and reliability of the elevator safety operation, and provides an innovative technical solution for elevator intelligent monitoring.

[0028] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent detection system adapted to the safe operation of an elevator, characterized in that, The system comprises: M1: a dynamic sensing module, deploying a movable sensor array inside the elevator shaft, which performs dynamic deployment according to the elevator state, obtains the vibration spectrum diagram, the acoustic fingerprint feature matrix and the door gap width change curve of the elevator; M2: an intelligent analysis module, including a physical analysis unit, an acoustic fingerprint analysis unit and a door system analysis unit, the physical analysis unit identifies the vibration mode through the vibration spectrum diagram and the preset fault feature library, and outputs the first risk value; the acoustic fingerprint analysis unit analyzes the acoustic fingerprint feature matrix, and obtains the second risk value in combination with the cumulative running mileage of the elevator; the door system analysis unit obtains the maximum door gap width and the standard deviation of the door gap width through the door gap width change curve, and further outputs the third risk value; M3: a hierarchical execution module, implementing a three-level response mechanism based on the first risk value, the second risk value and the third risk value; The elevator state is divided into a running state and a stop state; in the running state, the movable sensor array is gathered to the top of the elevator car; in the stop state, the movable sensor array is dispersed to move to the floor door area; The first risk value detects the vibration mode; the second risk value judges the guide rail wear abnormality; and the third risk value judges the door gap width abnormality.

2. The intelligent detection system adapted to the safe operation of an elevator according to claim 1, characterized in that, The movable sensor array includes a three-axis vibration sensor, an omnidirectional microphone and a radar sensor, The elevator state is divided into a running state and a stop state, and based on the running state and the stop state, the following deployment is performed respectively, 1) in the running state, the three-axis vibration sensor collects three-dimensional vibration signals of the elevator and transmits them to an edge computing node, the edge computing node obtains a vibration spectrum diagram through wavelet transform and fast Fourier transform, and simultaneously performs normalization processing on the vibration spectrum diagram; The omnidirectional microphone records the acoustic signals of the elevator, and further obtains an acoustic fingerprint feature matrix through wavelet transform and short-time Fourier transform; 2) in the stop state, the radar sensor emits electromagnetic waves and receives reflected signals, measures the door gap width between the elevator door and the floor door by using the frequency-modulated continuous wave principle, and forms a door gap width change curve.

3. The intelligent detection system adapted to the safe operation of an elevator according to claim 2, characterized in that, The physical analysis unit processes the vibration spectrum diagram through a convolutional neural network, and the convolutional neural network is trained through a preset fault feature library; outputting the vibration spectrum to a trained convolutional neural network to output a normal vibration probability value and an abnormal vibration probability value and an abnormal vibration probability value and calculating a first risk value, denoted as: wherein, represents the first risk value; represents an abnormal vibration score; represents a positive number; when the normal vibration probability value is greater than the abnormal vibration probability value, the first risk value of the elevator is 0, and the elevator is in a normal vibration mode; when the abnormal vibration probability value is greater than the normal vibration probability value, the first risk value is greater than 0, and the elevator is in an abnormal vibration mode.

4. The intelligent detection system adapted to the safe operation of an elevator according to claim 2, characterized in that, The voiceprint analysis unit determines the elevator running speed The fundamental frequency is calculated is expressed as: wherein denotes the distance between the rail joints; The voiceprint analysis unit extracts the amplitude of the harmonic component at the first integer multiple of the fundamental frequency through a peak detection algorithm, to form a voiceprint harmonic component vector and calculates a harmonic ratio, expressed as: wherein, represents the harmonic ratio; represents the amplitude of the fundamental frequency; represents the amplitude of the harmonic component; and represents the first integer multiple.​ The guide rail wear index is calculated by the harmonic ratio and the cumulative running distance of the elevator, and is expressed as: wherein, represents the guide rail wear index; represents the regression coefficient; represents the reference running distance; A wear threshold is set, when the guideway wear index is not greater than the wear threshold, there is no second risk value; when the guideway wear index is greater than the wear threshold, it is determined that a guideway wear abnormality occurs, and a second risk value is calculated, which is expressed as: wherein, represents the second risk value; represents a severity score of guideway wear; represents the wear threshold.

5. The intelligent detection system adapted to the safe operation of an elevator according to claim 2, characterized in that, The maximum door gap width is the maximum value among all sampling points on the door gap width change curve; The door gap width standard deviation is a statistical quantity of the dispersion degree of all data on the door gap width change curve, and is expressed as: wherein, represents the door gap width standard deviation; represents the door gap width value corresponding to the i-th sampling point; represents the i-th sampling point; represents the sampling point number; represents the mean value of the door gap width; A third risk value is calculated in combination with the door gap width maximum value and the door gap width standard deviation, and is represented as: wherein, the third risk value is represented as: respectively represent a weight coefficient of the door gap width maximum value and the door gap width standard deviation; respectively represent a reference value of the door gap width maximum value and the door gap width standard deviation. An abnormal door gap threshold is set, and when the third risk value is greater than the preset abnormal door gap threshold, it is determined that the door gap width abnormality occurs.

6. The intelligent detection system adapted to the safe operation of an elevator according to claim 3 or 4, characterized in that, The three-level response mechanism includes a first-level response mechanism, a second-level response mechanism and a third-level response mechanism, The implementation condition of the first-level response mechanism is that the first risk value is greater than 0, or the second risk value exists; The implementation condition of the second-level response mechanism is that the first risk value is greater than 0, and the second risk value exists.

7. The intelligent detection system adapted to the safe operation of an elevator according to claim 6, characterized in that, The third-level response mechanism is the highest level of safety response, and the implementation condition is that the third risk value is greater than the preset abnormal door gap threshold.

Images