An elevator fault diagnosis method and system

Abstract

The application relates to the technical field of elevator fault diagnosis, and discloses an elevator fault diagnosis method and system, which comprises the following steps: collecting elevator operation data, dividing an operation stage of an elevator operation process according to the elevator operation data, and calculating the residual error of the elevator operation data in the operation stage; based on the structure of the elevator, a cause-effect chain diagram reflecting the relationship between various components is established through fault mode analysis, and a direct upstream node set of a downstream node in the cause-effect chain diagram is taken as the parent set of the downstream node; in the operation stage, block replacement processing is performed on the upstream node residual error sequence of each edge in the cause-effect chain diagram to maintain the timing characteristics, a contrast residual error sequence is generated, and the propagation strength of the edge is calculated according to the contrast residual error sequence; effective propagation paths are screened according to the propagation strength of the edge, the effective propagation paths are sorted to obtain candidate nodes, the residual error of the candidate nodes is set to zero through virtual pinch-off, and forward propagation is performed through a semi-physical model, and a fault node is confirmed in the candidate nodes based on the forward propagation result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of elevator fault diagnosis, in particular to an elevator fault diagnosis method and system. BACKGROUND

[0002] With the continuous growth of the number and frequency of use of elevators, elevator safety and operational reliability are increasingly concerned. Traditional elevator fault diagnosis methods mainly rely on threshold judgment or simple logic triggering built-in the controller, such as detecting motor overcurrent, door machine timeout or brake failure, etc. This kind of method can find obvious hardware failure, but it is insufficient for progressive deterioration, cross-coupling abnormality or early fault symptom identification under multi-component linkage. In addition, the threshold is fixed and lacks environmental adaptation, often resulting in false positives or false negatives, making it difficult to meet the increasingly complex operating scenarios.

[0003] In recent years, some research attempts to introduce data-driven or model-driven residual analysis methods, but most of them stay at the single variable or local subsystem level, lacking causal relationship modeling across multiple modules such as traction, braking, door machine, etc. Existing residual inspection methods are mostly based on single-point statistics or filtering estimation, which cannot effectively separate "real propagation" from "common noise", thus lacking reliability under multi-source interference. At the same time, common algorithms fail to combine with engineering priors (such as physical symbol relationship, time delay range, component action logic), resulting in a lack of explainability of the diagnosis results, making it difficult for maintenance personnel to directly accept and apply.

[0004] Therefore, there is an urgent need for an elevator fault diagnosis method that can face multiple data sources, combine semi-physical period modeling and residual causal chain inspection, and have a verifiable closed loop, which can not only realize early warning, but also output executable maintenance guidelines. SUMMARY

[0005] In view of the above problems, the present application is proposed.

[0006] To solve the above technical problems, the present application provides the following technical solutions: An elevator fault diagnosis method, comprising: collecting elevator operation data, dividing the elevator operation process into operation stages according to the elevator operation data, and calculating the residual of the elevator operation data in the operation stage;

[0007] Based on the structure of the elevator, a causal chain diagram reflecting the relationship between each component is established through fault mode analysis, and the direct upstream node set of the downstream node in the causal chain diagram is taken as the parent set of the downstream node;

[0008] In the operation stage, the upstream node residual sequence of each edge in the causal chain diagram is subjected to block replacement processing to maintain the timing characteristics, to generate a contrast residual sequence, and the propagation strength of the edge is calculated according to the contrast residual sequence;

[0009] The effective propagation path is screened according to the propagation strength of the edge, the candidate node is obtained by sorting the effective propagation path, the residual error of the candidate node is zeroed by using virtual pinch-off, and forward propagation is carried out through a semi-physical model, and the fault node is confirmed in the candidate node based on the forward propagation result.

[0010] As a preferred scheme of the elevator fault diagnosis method, the elevator operation data includes traction system data, environment and load data, door machine system data and brake system data.

[0011] The traction system data includes current, DC bus voltage, car speed, car acceleration, motor output torque.

[0012] The environment and load data includes car load estimation, car position floor information, environment temperature and humidity.

[0013] The door machine system data includes current curve, action duration and door position sensor signal of the opening and closing process.

[0014] The brake system data includes brake coil on-off current, brake release and brake action time.

[0015] As a preferred scheme of the elevator fault diagnosis method, the operation stage is divided into start-up acceleration stage, uniform speed operation stage, deceleration stage, leveling and braking stage, opening door stage and closing door stage, wherein the start-up acceleration stage, the uniform speed operation stage and the deceleration stage are traction-related operation stages.

[0016] As a preferred scheme of the elevator fault diagnosis method, the residual error of the elevator operation data in the operation stage includes, in the traction-related operation stage, the motor output torque expectation is estimated by simplifying the dynamic relationship, the motor output torque expectation is equal to the sum of the inertia demand torque, the viscous damping torque, the gravity equivalent torque and the friction torque, and the motor output torque expectation is mapped to the current expectation and the DC bus voltage expectation.

[0017] In the leveling and braking stage, the brake coil on-off current expectation and the car speed expectation are constructed.

[0018] In the opening and closing stage, the action duration expectation and the current curve expectation of the opening and closing process are generated based on the door machine system data.

[0019] The elevator operation data is subtracted from the corresponding expectation to obtain the residual error of the elevator operation data.

[0020] As a preferred embodiment of the elevator fault diagnosis method described in this invention, the causal chain graph includes: using the residuals of elevator operation data as nodes of the causal chain graph, with one node corresponding to one residual; determining the causal relationship between nodes based on the physical working principle of the elevator system; establishing directed edges according to the direction from upstream cause to downstream result; and completing the establishment of the causal chain graph, wherein the node corresponding to the upstream cause is the upstream node, and the node corresponding to the downstream result is the downstream node.

[0021] In a causal chain graph, a directed edge directly connects to the upstream node of a downstream node, which is the direct upstream node of the downstream node. The set of direct upstream nodes of the downstream node is used as the parent set of the downstream node.

[0022] As a preferred embodiment of the elevator fault diagnosis method of the present invention, the block permutation process includes: during the operation phase, selecting a directed edge u→d in the causal chain graph, where u represents the upstream node, → represents the direction of the directed edge, and d represents the downstream node; extracting the residuals of u and d from the operation phase; and simultaneously extracting the residuals corresponding to the parent set of d.

[0023] Eliminating the interpretable influence of the remaining parent sets on d, we obtain new downstream information that is only related to u, and construct the conditional innovation quantity of the downstream node d, expressed as:

[0024] ;

[0025] in, Indicates the amount of conditional innovation; Represents the residual of d; Indicates downstream node The set of all residuals except u in the parent set; Indicates that in a given Under the conditions, for The conventional estimate;

[0026] Estimate upstream residuals The short-term correlation structure is calculated during the runtime phase. The autocorrelation decay time, combined with the sampling frequency, is converted into the number of sample points to obtain the block length, expressed as:

[0027] ;

[0028] in, Represents the residual of u; Indicates the length of the block used for the substitution; express The autocorrelation decay time; Indicates the sampling frequency; This represents the floor operator;

[0029] Performing a cyclic block permutation, Divide into several consecutive blocks, each block length L, randomly rearrange the order of the blocks in units of blocks, and allow the first and last to be spliced to form a ring arrangement, the timing within the block remains unchanged, and the permutation sequence is obtained, And Remain unchanged, only replace the upstream node u with the permutation sequence, and construct the counterfactual control of the short-term structure of the upstream node;

[0030] The conditional innovation quantity is As a downstream response, compare the difference in explanatory power of the conditional innovation quantity between the upstream node u and the permutation sequence, and calculate the two conditional scores of the upstream node u and the permutation sequence using the conditional correlation scoring function, and take the difference between the two times as the propagation strength;

[0031] Do B times of independent cyclic block permutation to obtain the empirical distribution of the propagation strength, calculate the significance by permutation test, and B represents the number of permutations with a positive integer value;

[0032] In the running phase, estimate the main lag position of the upstream node to the downstream node, for the directed edge u→d, output the propagation strength, significance and main lag position.

[0033] As a preferred scheme of the elevator fault diagnosis method, wherein: the sorting of the effective propagation path to obtain the candidate node includes, for each node in the effective propagation path, counting the edge set and the incoming edge set, the outgoing edge set is all downstream node edges pointed to by the node as an upstream node, and the incoming edge set is all edges pointed to it from other nodes as a downstream node;

[0034] A root cause score is defined for each node, and the root cause score is composed of output contribution, input weakening and node residual energy. The output contribution is the sum of the propagation strength of all outgoing edges of the node, the input weakening is the sum of the propagation strength of all incoming edges of the node, and the node residual energy is the mean square of the residual of the node in the running phase. The root cause score is represented as the output contribution of the node minus the input weakening plus the node residual energy;

[0035] Calculate the root cause score for all nodes, sort the root cause nodes in descending order of root cause score value, and form a root cause node sorting table.

[0036] As a preferred scheme of the elevator fault diagnosis method, wherein: the virtual pinch-off includes selecting the first node in the root cause node sorting table as the target root cause, and taking out the outgoing edge set of the target root cause;

[0037] Under the premise of not changing other parent sets and running stages, the residual of the target root cause is artificially set to zero, and the magnitude of the predicted downstream residual rollback is propagated forward from this, and a corresponding prediction curve is generated, for each downstream node, the predicted rollback trajectory is compared with the current residual, and the predicted rollback ratio is calculated.

[0038] An elevator fault diagnosis system adopting any method of the present application, wherein: a collection module collects elevator operation data, divides the elevator operation process into running stages according to the elevator operation data, and calculates the residual of the elevator operation data in the running stages;

[0039] An analysis module, based on the elevator structure, establishes a causal chain diagram reflecting the relationship between components by fault mode analysis, and takes the direct upstream node set of the downstream node in the causal chain diagram as the parent set of the downstream node;

[0040] A replacement module, in the running stages, performs block replacement processing on the upstream node residual sequence of each edge in the causal chain diagram to generate a contrast residual sequence, and calculates the propagation strength of the edge according to the contrast residual sequence;

[0041] A positioning module, according to the propagation strength of the edge, screens effective propagation paths, sorts the effective propagation paths to obtain candidate nodes, sets the residual of the candidate nodes to zero by virtual clamping and performs forward propagation through a semi-physical model, and confirms the fault node in the candidate nodes based on the forward propagation result.

[0042] The present application has the following advantages: the method of the present application can accurately identify abnormal relationships of traction, braking, door machine and other subsystems under multi-source data through running stage division, semi-physical expectation generation and residual construction, causal chain diagram modeling and block replacement propagation verification. Under the premise of preserving short-term correlation, counterfactual contrast is constructed to quantify the propagation strength by conditional score difference, ensuring that the causal chain has statistical significance and conforms to the logic of science and technology. On this basis, root cause scoring is used to sort nodes, highlighting the source of abnormality; and a observable closed loop is formed by virtual clamping and retesting, significantly improving the reliability, adaptability and engineering operability of diagnosis. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. 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.

[0044] Figure 1 A whole flowchart of an elevator fault diagnosis method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present application.

[0046] Embodiment 1, refer to Figure 1 For an embodiment of the present application, an elevator fault diagnosis method is provided, comprising:

[0047] S1: collecting elevator operation data, dividing the elevator operation process into operation stages according to the elevator operation data, and calculating the residual of the elevator operation data in the operation stage.

[0048] The present application first establishes an analysis framework in stages, divides a complete elevator operation process into stages with clear physical meaning and repeatable identification, and slices the multi-source data in each stage, so that the subsequent analysis is compared under similar working conditions.

[0049] In order to support stage division and data slicing, multiple signals are collected through the existing control system and conventional sensors of the elevator, and a unified and quality control mechanism is formed through time stamp to form a neat multi-channel data stream. The system collects and synchronizes the following data in real time: motor three-phase current, DC bus voltage, car speed, car acceleration, motor output torque, brake coil on-off current, brake release and brake action time, current curve of door opening and closing process, action duration, door position sensor signal, car load estimate, car position floor information, ambient temperature and humidity. All channels are time-stamped, deburred, band-limited smoothed, missing data compensated and resampled aligned, and data quality identifiers are retained to constrain the sampling range of subsequent self-calibration.

[0050] The stage division is completed according to the working logic of the elevator mechanical and electrical system and the joint characteristics of the signals. The typical states of the elevator operation state include: starting from static to starting (continuous rise of car speed from zero, synchronous lifting of motor three-phase current and motor output torque), reaching and maintaining constant speed (stable car speed, limited motor three-phase current fluctuation), deceleration near the target floor (continuous decrease of car speed, DC bus voltage showing regenerative or traction corresponding steady-state fluctuation mode), leveling and braking (car speed converging to leveling range and brake coil on-off current showing clear action), and door opening and closing (current curve of door opening and closing process showing starting peak, platform and end alignment disturbance characteristics, and door position sensor signal changing in expected timing).

[0051] The system adopts a state machine form to continuously distinguish the above-mentioned stages on the time axis: the trend of speed and acceleration cooperates with the joint change of motor three-phase current and motor output torque to determine the start, uniform speed and deceleration; the steady voltage level of the DC bus and the energy feedback characteristics serve as the side evidence of the deceleration end and the leveling; the action edge of the brake coil on-off current and the convergence of the car speed jointly determine the leveling and braking window; the door opening and closing rely on the current curve, the action duration and the door position sensor signal logic of the door opening and closing process to identify. For complex working conditions such as mid-way parking, re-leveling, secondary start-stop and the like, the state machine allows to set sub-states under the same major stage to mark the transition behavior, but all windows have clear stage labels and direction attributes (uplink / downlink).

[0052] When the stage boundary is identified, the system will cut the multi-channel data in the corresponding time range into a window, and a small amount of transition margin is reserved at both ends of the window to completely record the dynamics near the boundary. Each window carries context information related to diagnosis, including direction, start and end floors (given by the car position floor information), car load estimate, ambient temperature and humidity, whether energy feedback occurs, specific actions of door opening / closing and braking action timing, etc. The above stage and slicing process aligns the same working conditions under different dates, different seasons and different passenger flows on a comparable basis, laying a stable data foundation for subsequent expectation generation and residual construction.

[0053] Further, in each operating stage, in combination with the conventional relationship between dynamics and electrical side, the expectation quantity is generated for the collected quantity related to the stage, and the deviation of "measured-expected" is uniformly constructed. To avoid parameter rigidity, the parameters of all expectation quantities are based on recent healthy windows, and robust statistics with forgetting factor are used for self-calibration, maintaining migratability under different equipment, different seasons and different load conditions.

[0054] Specifically, in the traction-related stage, the system generates the motor output torque expectation based on the simplified dynamics relationship, and then maps it to the motor three-phase current expectation; the steady voltage level of the DC bus gives the DC bus voltage expectation (used for early identification of voltage stabilization and feedback abnormalities) according to the nominal voltage stabilization target of the device, combined with the load state and temperature factors. The motor output torque expectation is represented as:

[0055] ;

[0056] wherein, represents the motor output torque expectation; represents the equivalent moment of inertia; represents the angular acceleration, which is obtained by converting the car acceleration and transmission ratio or by differentiating the car speed value; represents the equivalent viscous damping coefficient; ω represents angular velocity, converted from car velocity and gear ratio or estimated by driver; g represents gravity equivalent term, estimated from car load estimate, direction and floor displacement; f represents friction equivalent term; t represents time.

[0057] The motor output torque expectation is mapped to current expectation and DC bus voltage expectation, the current expectation is represented as:

[0058] ;

[0059] wherein, I represents current expectation; K represents torque constant; B represents equivalent bias of current measurement and control dead zone.

[0060] The DC bus voltage expectation is given according to the voltage stabilization target and operating state of the driver: the system is centered on the nominal voltage stabilization value of the device, combined with the slow drift caused by environmental temperature and humidity on the characteristics of the device, and the temperature-load corrected voltage stabilization expectation formed by the load change (indirectly reflected through the motor output torque expectation and the motor three-phase current expectation), and the controlled short-time surge or ripple bandwidth is allowed to appear in the deceleration scenario of regenerative braking; the expectation is used for comparison with the DC bus voltage, so as to identify abnormal voltage stabilization deviation and feedback abnormalities.

[0061] In the leveling and braking phase, the system synchronously generates the braking coil on-off current expectation and the car velocity expectation (final segment convergence). The former adopts a "rise-maintain-decay" templated profile, and the parameters are obtained from the statistics of the healthy window and are fine-tuned according to the environmental temperature and humidity; the latter adopts a "uniform deceleration to leveling velocity range" convergence model, and the parameters are lightly corrected according to the car position floor information and the car load estimate, so as to maintain causal consistency with the action edge of the braking coil on-off current.

[0062] In the opening and closing door phase, the system generates the action duration expectation and the current curve expectation of the opening and closing door process according to the timing and logic of the door position sensor signal. Among them, the action duration expectation adopts a "acceleration-constant speed-deceleration" three-segment kinematics template, and is slowly corrected according to the environmental temperature and humidity and the near-period use frequency (hot / cold); the current curve expectation of the opening and closing door process adopts a "start peak-plateau-end alignment disturbance" three-segment load profile, and the parameters are slowly updated according to the long-term guide rail cleanliness and door width characteristics, and are aligned with the key nodes of the door position sensor signal to constrain the timing of the end alignment.

[0063] It should be noted that in the flat layer, braking and door machine opening and closing stages, the "template profile" and "convergence model" used by the present application are both conventional engineering modeling methods in the field, and the core idea is to use simple and fixed function forms to fit and describe common execution component action processes. The "rise-maintain-decay" template profile refers to signals such as brake coil current, which has typical on-off characteristics, and its action process usually shows rapid current rise, maintenance for a period of time within a certain amplitude range, and then gradually decays to zero. The industry generally uses this three-section curve to represent the action process of electromagnetic brakes. The "final uniform deceleration to flat layer speed range" convergence model refers to the fact that the car will gradually reduce speed according to the law of uniform deceleration before reaching the station, until it approaches zero speed and enters the flat layer interval. This deceleration convergence model is the basis of elevator flat layer control and belongs to mature control law. The "acceleration-constant speed-deceleration" kinematics template is commonly used to describe the door machine opening and closing time curve, i.e. the door panel first accelerates to start, then runs at a substantially constant speed, and finally slows down to align near the end. The industry widely uses this three-section time model as a reference for opening and closing door performance evaluation; the "start peak-plateau-end alignment disturbance" current profile template corresponds to the load characteristics of the door machine on the electrical side, i.e. the current appears a peak value at start, maintains a plateau value during running, and has a small fluctuation at the end due to damping or alignment effect.

[0064] After generating the above-mentioned expected trajectory and event baseline, the system constructs a unified residual representation within the current window. Specifically, in each operating phase, all residuals are defined as the difference between the elevator operating data and the corresponding expected value, represented as:

[0065] Motor three-phase current residual = motor three-phase current - motor three-phase current expected;

[0066] DC bus voltage residual = DC bus voltage - DC bus voltage expected;

[0067] Car speed residual = car speed - car speed expected (flat layer section);

[0068] Car acceleration residual = car acceleration - car acceleration expected;

[0069] Motor output torque residual = motor output torque - motor output torque expected;

[0070] Brake coil on-off current residual = brake coil on-off current - brake coil on-off current expected;

[0071] Action duration residual = action duration - action duration expected;

[0072] Current curve residual of opening and closing process = current curve of opening and closing process - current curve of opening and closing process expected.

[0073] To achieve comparability between different dimensions and different phases, the system normalizes the residuals. Normalization does not change the mapping relationship between expectation and residual, but puts residuals of different dimensions on a unified scale, facilitating threshold setting, statistical testing and cross-dimension comparison in subsequent steps. Residuals and normalized residuals are stored together with contextual information of the operating phase (direction, car position floor information, car load estimate, ambient temperature and humidity, data quality identifier) for subsequent diagnostic reasoning and model self-updating.

[0074] S2: Based on the elevator structure, a causal chain diagram reflecting the relationship between each component is established through failure mode analysis, and the direct upstream node set of the downstream node in the causal chain diagram is taken as the parent set of the downstream node.

[0075] Further, after completing the phasing and residual construction, the causal chain diagram covering the traction system, braking system, door machine system and electrical energy supply link is established based on the physical mechanism of the elevator mechanical and electrical system, control logic and maintenance experience. The nodes of the causal chain diagram are represented by residuals, i.e. the motor three-phase current residual, DC bus voltage residual, car speed residual, car acceleration residual, motor output torque residual, brake coil on-off current residual, action duration residual, current curve residual of opening and closing door process, etc. To improve the explainability and stability of causal relationship, the establishment of the graph follows the principle of "physical cause first, signal consequence second": the directionality is determined in priority according to the mechanical, electrical and control links between components, supplemented by known associations in the maintenance manual, FMEA failure mode analysis conclusions and statistical confirmation of historical health samples. For different phases (start, constant speed, deceleration, leveling and braking, opening door, closing door) and different directions (up, down), the graph structure allows slight differences, and the system maintains corresponding sub-graphs to separately depict the causal paths specific to each phase.

[0076] In the traction-related phase, the motor output torque residual is considered as the upstream driving quantity of the traction link. If the motor output torque residual deviates, it will first be reflected in the motor three-phase current residual, and further affect the fluctuation of the DC bus voltage residual and the DC side power through energy transmission; at the same time, there is a causal relationship between the motor output torque residual and the car speed residual, car acceleration residual, especially in the start and deceleration phases. Based on this, the system sets a directed edge from the motor output torque residual to the motor three-phase current residual, a directed edge from the motor three-phase current residual to the DC bus voltage residual in the traction sub-graph, and according to the characteristics of the phase, sets directed edges from the motor output torque residual to the car speed residual, from the car speed residual to the DC bus voltage residual, etc.

[0077] For the braking phase, the braking coil on-off current residual directly affects the convergence behavior of the last segment of the car speed residual, and has an observable impact on the DC bus voltage residual during regenerative braking. Therefore, a directed edge is set from the braking coil on-off current residual to the car speed residual and the DC bus voltage residual in the braking subgraph.

[0078] For the door machine system, the current curve residual of the opening and closing process reflects the deviation of the door machine load and driving state, which can cause the systematic lengthening or shortening of the action duration residual, and eventually present the abnormalities such as leading, lagging or jitter in the door position sensor signal residual. Therefore, a directed edge is established in the door machine subgraph in the order of “current curve residual of the opening and closing process→action duration residual→door position sensor signal residual”.

[0079] The direction and existence of the above directed edge are based on the device structure and control flow, and the rationality of the directed edge can be statistically verified in combination with historical health samples. To avoid unnecessary complexity, the graph structure is designed in a top-down hierarchical manner, and the influence of the intrinsic coupling relationship is weakened by staging and timing constraints.

[0080] In the causal chain graph, through a directed edge, the upstream node directly connected to the downstream node is the direct upstream node of the downstream node. The direct upstream node set of each node is the parent set of the node. The parent set only contains the residuals that have a direct causal impact on the node, avoiding the introduction of remote variables that span multiple intermediate links, to ensure the explicitness of the explanation and the controllability of the calculation. For example, the parent set of the motor three-phase current residual usually only contains the motor output torque residual; the parent set of the DC bus voltage residual contains the motor three-phase current residual and the car speed residual; the parent set of the action duration residual contains the current curve residual of the opening and closing process; the parent set of the door position sensor signal residual contains the action duration residual; the parent set of the car speed residual contains the motor output torque residual in the starting and deceleration phase, and the braking coil on-off current residual in the leveling and braking phase. For the ambient temperature and humidity and the car load estimation value, the system regards them as slow variables that have been corrected on the expectation side and does not directly include them in the parent set of the residual node.

[0081] To enhance the engineering constraints of the parent-child relationship, the system simultaneously registers the expected influence sign and the allowed time delay range on each directed edge. The influence sign is used to express the typical directional relationship of the upstream residual to the downstream residual, such as the increase in the motor output torque residual usually leading to the increase in the motor three-phase current residual; the allowed time delay range reflects the time window required for mechanical, electrical or control link propagation, such as the influence of the brake coil on-off current residual to the car speed residual usually occurring within a limited time delay of milliseconds to seconds. These information comes from the device structure, control cycle and statistical estimation of historical samples, which will be used as consistency gating conditions in subsequent steps. For nodes with multiple candidate upstreams, the system preferentially retains the upstream that can be explicitly explained by physical mechanisms, and if there is a conflict of equivalent explanation, the priority is set according to the stage characteristics and maintenance experience, and if necessary, the directed edges with low priority are disabled to ensure the sparsity and stability of the parent set.

[0082] Further, after the parent set is determined, the system constructs a conditional innovation quantity for each node within each running stage. The so-called conditional innovation quantity refers to the remaining part of the node residual that cannot be explained after considering the influences that can be explained by its parent set. In engineering implementation, the system first uses the parent set residual to perform the regular conditional elimination processing on the current node residual within the same window, such as eliminating the trend, amplitude and hysteresis components driven by the parent set, and then the remaining unexplained components are taken as the conditional innovation quantity of the node in the current window.

[0083] It should be noted that the conditional innovation quantity represents the new abnormal information of the node relative to its direct upstream, reducing the redundancy brought by upstream propagation; on the other hand, it provides a clear contrast for subsequent propagation inspection, so that the system can judge whether the disturbance of a certain upstream residual has left a repeatable influence trace on the downstream node. For windows with poor data quality (such as obvious missing, saturation or time misplacement), the system will limit the window from participating in elimination and contrast before constructing the conditional innovation quantity, so as not to mistake noise as unexplained components.

[0084] S3: In the running stage, perform block replacement processing on the upstream node residual sequence of each edge in the causal chain diagram to generate a contrast residual sequence, and calculate the propagation strength of the edge according to the contrast residual sequence.

[0085] Further, after the establishment of the causal chain diagram and the acquisition of the parent set and the conditional innovation of each node, the propagability of any directed edge is tested in the running stage. Specifically, if an upstream residual is truly driving a downstream residual, then when we only change the time structure of the upstream while keeping the other quantities of the parent set and the downstream unchanged, the downstream should show significant differences in its conditional innovation; conversely, if the differences disappear, it is more likely to be co-driving or accidental coherence. The present application thus constructs the original- counterfactual contrast, and the difference in explanatory power of the two under the same parent set conditions is defined as the propagation strength of the edge.

[0086] In the running stage, a directed edge u→d in the causal chain diagram is selected, u represents an upstream node, → represents the direction of the directed edge, and d represents a downstream node. The residual of u and the residual of d are taken out from the running stage, and the residuals corresponding to the parent set of d are also taken out, so as to eliminate the explainable influence of the remaining parent set on d, obtain new information of the downstream related only to u, and construct the conditional innovation of the downstream node d, which is represented as:

[0087] ;

[0088] Among them, represents the conditional innovation; represents the residual of d; represents the parent set of the downstream node , except for u; represents the conventional estimated value of under the condition of .

[0089] In order to make the “counterfactual” both disturb the short-term time structure of the upstream and not destroy the amplitude distribution and the intra-block correlation, the present application adopts a cyclic block permutation matching the autocorrelation time of the upstream residual. Specifically, the autocorrelation decay time of the upstream residual is first measured in the current window, and the block length is obtained by making a conventional conversion with the sampling frequency, so that the permutation rearranges in blocks as the minimum unit, and the intra-block time sequence remains completely unchanged. The block length L is given by the following formula:

[0090] ;

[0091] Among them, represents the residual of u; represents the block length for permutation; represents the autocorrelation decay time of ; represents the sampling frequency; denotes the upward rounding operator. The block length determined by the relevant time adaptation can preserve the upstream short-term spectral shape and autocorrelation, thus constructing a more realistic counterfactual of how the upstream driver would behave when disturbed, which is particularly crucial for periodic disturbances in elevator field, cogging effect, and door machine rhythm, etc.

[0092] After obtaining the block length, only the upstream residual of the directed edge is subjected to the cyclic block permutation, while the other parent set residuals and downstream residuals remain unchanged, so as to precisely limit the permutation effect to one directed edge of the causal chain. For example, in the estimation of the torque residual→motor three-phase current residual traction link, only the estimated torque residual is subjected to cyclic block permutation, without disturbing the motor three-phase current residual and other quantities in the parent set; in the brake coil on-off current residual→car speed residual braking link, only the brake coil on-off current residual is subjected to permutation, without changing the car speed residual and the rest of the parent set. Such directed edge positioning avoids the confusion caused by the traditional integer permutation disturbing multiple paths, and makes the propagation test strictly correspond to whether this directed edge is established.

[0093] Specifically, the cyclic block permutation is performed to divide into a plurality of continuous blocks, each block having a length L, randomly rearranging the order of the blocks in units of blocks, and allowing the first and last to be spliced to form a ring-shaped arrangement, the time sequence in the block being unchanged, to obtain a permutation sequence, and remaining unchanged, only replacing the upstream node u with the permutation sequence to construct a counterfactual of the short-term structure of the upstream node being disturbed.

[0094] To quantify the difference between the original and the counterfactual, the conditional innovation quantity is taken as the downstream response, the difference in explanatory power of the upstream node u and the permutation sequence for the conditional innovation quantity is compared, and the conditional correlation score function is used to calculate the conditional score of the upstream node u and the permutation sequence twice, and the difference between the two times is taken as the propagation strength.

[0095] The conditional correlation score function can be selected by conditional distance correlation, conditional mutual information, or partial-HSIC standard implementation in engineering. The conditional score difference distinguishes causal propagation from common driving / co-temporal noise. Because the parent set condition is fixed and the explained part of the downstream is excluded, only when the time structure of the upstream really leaves a repeatable impact on the downstream, the propagation strength will be significantly positive; otherwise, the difference will be close to zero.

[0096] Considering the influence of field noise and accidental impact, multiple independent permutations are introduced to obtain empirical values, and a significance measure is given accordingly to avoid the contingency of single comparison. By doing B times independent cyclic block permutation on the upstream residual, a group of propagation intensity samples is obtained, and the empirical value is calculated according to the conventional method of permutation test. When the empirical value is small enough and remains stable within adjacent windows, it is confirmed that the directed edge has statistical significance of propagation, which is represented as:

[0097] ;

[0098] wherein, represents the empirical value; represents the number of permutations, which is a positive integer; b represents the bth permutation; represents the propagation intensity obtained by the bth permutation; represents the initial propagation intensity; represents an indicator function, which takes a value of 1 when the condition in the parentheses is met.

[0099] To be consistent with the subsequent symbol-time lag consistency gating, the dominant time lag position of the upstream to the downstream is estimated synchronously within the running phase (for example, the brake link usually takes effect in the range of milliseconds to seconds, and the traction link takes effect in the control period). The dominant time lag position is represented as:

[0100] ;

[0101] wherein, represents the dominant time lag position; represents the independent variable corresponding to the maximum value; represents the candidate time lag position; represents the time lag window allowed by the device; represents the correlation coefficient; represents the upstream node residual at time The dominant time lag will enter the gating link together with the expected influence symbol of the directed edge and the allowed time lag window of the device a priori, to filter out statistically significant but engineering unfeasible false propagation.

[0102] In engineering implementation, the application gives application examples of several typical directed edges:

[0103] In the directed edge of estimating the torque residual→motor three-phase current residual, the propagation intensity is significant and the dominant time lag falls within the control period, which usually indicates that the compensation on the drive side is insufficient or the friction and load estimation deviate;

[0104] In the directed edge of brake coil on-off current residual→car speed residual, if the propagation intensity is significantly persistent during regenerative deceleration, and the dominant time lag appears immediately along the directed edge, it indicates that the brake hysteresis or brake gap is abnormal;

[0105] In the directed edge of the current curve residual of the opening and closing process to the action duration residual, if the propagation intensity is significant and intensified in the terminal alignment stage, it often corresponds to poor guide rail lubrication or door block wear. These conclusions are derived from the control and quantification of the cyclic block replacement conditional score difference, rather than a single threshold criterion, thus having better interpretability and retest consistency.

[0106] To adapt to different equipment and environment, the present application sets up robust protection for abnormal or degraded scenarios: when the upstream residual is approximately white noise and cannot obtain reliable correlation time, the block length is limited to the minimum available range and the confidence weight of the propagation conclusion is reduced; when the quality identifier of the stage window is unqualified (such as obvious missing sampling or clock misplacement), the propagation result of the window does not participate in aggregation; when the upstream or downstream is in saturation or clipping state, the replacement is suspended and restored in the next healthy window. The above protection strategies ensure that the statistical inference is not "biased" by low-quality data.

[0107] In summary, the present application, through the three elements of correlation time adaptive block length, cyclic block replacement and original- counterfactual conditional score difference, constitutes a propagation verification mechanism that can run in real time on the edge and can be verified by engineers. The propagation intensity, empirical value and dominant time lag output will directly enter the subsequent symbol-time lag consistency gating and root cause score aggregation, providing reliable and traceable evidence chain for early identification and root cause localization of elevator faults without changing the existing acquisition and control architecture.

[0108] S4: screening effective propagation paths according to the propagation intensity of the edges, sorting the effective propagation paths to obtain candidate nodes, setting the candidate node residual to zero by virtual pinch-off and performing forward propagation through a semi-physical model, and confirming the fault node in the candidate nodes based on the forward propagation result.

[0109] Further, after completing the residual propagation verification, significance determination and engineering prior gating, the present application obtains a purified causal chain graph. In the graph, each node corresponds to the residual of the aforementioned acquisition data, such as motor three-phase current residual, DC bus voltage residual, car speed residual, car acceleration residual, estimated torque residual, brake coil on-off current residual, action duration residual, current curve residual of the opening and closing process, and door position sensor signal residual; each directed edge represents a statistically significant, physically reasonable propagation relationship between the upstream residual and the downstream residual.

[0110] In constructing the purified causal chain graph, a strict triple judgment method is adopted for the retention of directed edges: first, the propagation strength must be greater than zero and reach a preset threshold within the phase window, ensuring that the propagation is not random noise; second, the propagation strength must remain significant under multiple cycle block replacements, i.e., the empirical value is less than the significance level (such as 0.05), otherwise the directed edge is considered not to exist; finally, the dominant time lag and sign of the propagation must conform to engineering priori, for example, the estimated torque residual→motor three-phase current residual should be positively correlated and the time lag should not exceed the drive control period. Only the directed edges that meet all three conditions are retained to enter the subsequent scoring process, and the rest of the directed edges are excluded in the graph construction. This processing can ensure that the retained propagation relationship has both statistical significance and conforms to the physical law of the equipment, thereby avoiding misjudgment caused by accidental correlation or abnormal noise.

[0111] After obtaining the purified causal chain graph, the root cause degree of each node is quantified. Specifically, the system first calculates the sum of the propagation strengths of all outgoing edges of the node as the contribution of the node to the external diffusion of anomalies; at the same time, the sum of the propagation strengths of all incoming edges is calculated as the degree of dependence of the node on the upstream. The incoming edge refers to the directed edge pointing to the node, and the outgoing edge refers to the directed edge pointing from the node to other nodes. If a node has a significant impact on the downstream propagation, but is less dependent on the upstream, it is more likely to be the root cause. In order to avoid one-sided judgment based on propagation relationship alone, the present application further introduces the residual energy of the node itself as a supplementary index, i.e., the energy or mean square value of the node residual is calculated within the phase window to measure the magnitude of the node deviating from the expectation. In this way, the root cause score of each node is composed of three parts: external contribution—internal dependence + residual energy.

[0112] In actual operation, the root cause score of all nodes is calculated according to the above rules, and the nodes are sorted according to the score. The node with the highest score often shows strong residual energy and can propagate anomalies to multiple downstream nodes, while its incoming edge is weak, indicating that the node is more likely to be the root cause. For example, if the estimated torque residual consistently produces significant propagation to the motor three-phase current residual and the DC bus voltage residual in multiple windows, and its own residual energy is also large, while its incoming edge has limited impact, the system will determine it as a potential root cause of the traction system; similarly, if the brake coil on-off current residual has a stable impact on the car speed residual and the DC bus voltage residual, the brake system can be marked as a suspicious source. Finally, the present application outputs a root cause node ranking table, which lists the root cause score, ranking and key propagation path of each node, for maintenance personnel to quickly locate the fault starting point.

[0113] Further, after completing the root cause node scoring and sorting, based on the size of the node score, the range of the propagation path and the strength of the residual energy, further generate fault alarms and hierarchical processing. Specifically, the system marks the nodes with high root cause score and stable in multiple windows as high-risk sources, combines the breadth of the propagation range and the number of affected downstream nodes, and divides abnormal events into different levels, for example: level I alarm corresponds to root cause nodes with significant safety hazards, extensive propagation and significant residual energy; level II alarm corresponds to nodes with function degradation, limited propagation or medium residual energy; level III prompt is used for early deviation or slight abnormal nodes.

[0114] After completing the classification, the system automatically generates maintenance guidelines for maintenance personnel in combination with the physical meaning in the causal chain diagram and the engineering knowledge base. Specifically, if the estimated torque residual in the traction link is marked as the root cause, the system will prompt to check the motor excitation, driver parameters or load estimation link; if the high-level alarm occurs in the brake coil on-off current residual, it prompts to check the brake coil, brake clearance or control relay; if the current curve residual of the opening and closing process is continuously abnormal, it prompts to check the door machine motor, guide rail lubrication state or door lock mechanism. The maintenance guide content includes not only the components that need to be paid attention to first, but also the recommended detection order and alternative quick troubleshooting methods, so that the alarm information can directly guide operation and maintenance.

[0115] Further, after the root cause is located, the system does not directly use statistical significance as the final basis, but gives maintenance personnel a quantitative rollback commitment that can be verified by retesting through virtual clipping.

[0116] Virtual clipping refers to artificially setting the residual of the root cause node to the health baseline in the online data space without changing the actual device, and then deducing its natural impact on downstream residuals. Specifically, the first node in the root cause node ranking table is selected as the target root cause , the out-edge set of the target root cause is taken out, the residual of the target root cause is artificially set to zero without changing other parent sets and running stages, and the magnitude of the downstream residual rollback is predicted by forward propagation, and the corresponding prediction curve is generated, represented as:

[0117] ;

[0118] Wherein, represents the residual prediction value of downstream node d after the root cause node is virtually clipped; represents the measured value of the residual of downstream node d; represents the target root cause The interpretable component caused to the downstream node d by the directed edge.

[0119] To make the commitment comparable, the system records the context constraints related to the window, including floor pair (given by the car position floor information), direction, car load estimate, ambient temperature and humidity, and whether energy feedback occurs, at the same time when generating the prediction rollback list. Maintenance personnel arrange retests under similar conditions according to this, to ensure that the windows before and after maintenance are comparable. After the retest is completed, the system takes the residual energy comparison before and after maintenance as the objective acceptance standard: when the predicted rollback is verified on the key downstream residual, and occurs in the key period consistent with the prediction (such as the end of deceleration, the end of door alignment, etc.), the system can determine that the root cause is established; if the rollback is insufficient or the period is not consistent, the system automatically reverts to the alternative root cause, or prompts to perform group action verification. To avoid misjudgment caused by noise or single occurrence, the system performs consistency check on multiple adjacent windows: only when the rollback amplitude and period are stable and repeated in adjacent windows, the maintenance is considered to be passed.

[0120] Through the above closed-loop mechanism, the application closely connects statistical inference with engineering practice: virtual pinch turns the propagation conclusion of upstream-downstream into measurable, comparable, and verifiable rollback commitment; retest comparison provides objective acceptance standard for alarm and maintenance.

[0121] In an exemplary embodiment, an elevator fault diagnosis system is also provided, comprising: a collection module that collects elevator operation data, divides an elevator operation process into operation stages according to the elevator operation data, and calculates residuals of the elevator operation data in the operation stages.

[0122] An analysis module that, based on the elevator structure, establishes a cause-effect chain diagram reflecting the relationship between components by fault mode analysis, and takes the direct upstream node set of a downstream node in the cause-effect chain diagram as the parent set of the downstream node.

[0123] A replacement module that, in the operation stages, performs block replacement processing that maintains the timing characteristics on the upstream node residual sequence of each edge in the cause-effect chain diagram, generates a comparison residual sequence, and calculates the propagation strength of the edge according to the comparison residual sequence.

[0124] A positioning module that filters effective propagation paths according to the propagation strength of the edge, sorts the effective propagation paths to obtain candidate nodes, sets the residuals of the candidate nodes to zero by virtual pinch and performs forward propagation through a semi-physical model, and confirms the fault node in the candidate nodes based on the forward propagation result.

[0125] If the above functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or parts of the present application that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0126] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device, or in conjunction with these instruction execution systems, apparatus, or devices.

[0127] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CD ROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by editing, interpreting, or otherwise processing the program as necessary, and then storing it in a computer memory.

[0128] It should be understood that portions of the present application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, implementation can be with any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0129] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. An elevator failure diagnosis method characterized by comprising: The method comprises: collecting elevator operation data, dividing an operation stage of an elevator operation process according to the elevator operation data, and calculating a residual error of the elevator operation data in the operation stage; based on the elevator structure, a cause-effect chain diagram reflecting the relationship between each component is established through failure mode analysis, in the cause-effect chain diagram, through a directed edge, the upstream node directly connected to the downstream node is the direct upstream node of the downstream node, and the set of the direct upstream nodes of the downstream node in the cause-effect chain diagram is taken as the parent set of the downstream node; in the operation stage, a block replacement processing of maintaining the time sequence characteristics of the upstream node residual error sequence of each edge in the cause-effect chain diagram is performed to generate a contrast residual error sequence, and the propagation strength of the edge is calculated according to the contrast residual error sequence; the block replacement processing comprises, in the operation stage, selecting a directed edge u→d in the cause-effect chain diagram, u representing the upstream node, → representing the direction of the directed edge, and d representing the downstream node, taking out the residual error of u and the residual error of d from the operation stage, and simultaneously taking out the residual error corresponding to the parent set of d; eliminating the explainable influence of d on the rest of the parent set to obtain new downstream information related only to u, and constructing the conditional innovation quantity of the downstream node d, which is represented as: ； wherein, represents the conditional innovation quantity; represents the residual of d; represents the set of all residuals in the parent of downstream node except u; represents the regular estimate of given the condition ; Estimate the short-term correlation structure of the upstream residuals Calculate the autocorrelation decay time of the upstream residuals during the run phase Convert the sampling frequency to sample points to obtain the block length, expressed as: ； wherein, denotes a residual of u; denotes a block length for permutation; denotes an autocorrelation decay time of denotes a sampling frequency; denotes a ceiling operator; Performing cyclic block permutation, the sequence is Divide the sequence into several continuous blocks with length L, randomly rearrange the order of the blocks, and allow the first and last blocks to be spliced to form a circular arrangement. The timing within the block remains unchanged, and the permutation sequence is obtained, And Keep it unchanged, just replace the upstream node u with the permutation sequence, and construct the counterfactual control of the short-term structure of the upstream node being disturbed. The conditional innovation quantity As a downstream response, the difference in the explanatory power of the conditional innovation quantity between the upstream node u and the permutation sequence is compared, and the conditional scores of the upstream node u and the permutation sequence are calculated using a conditional correlation scoring function, and the difference between the two conditional scores is taken as the propagation strength. B independent cyclic block replacements are performed to obtain an empirical distribution of the propagation strength, the significance is calculated through the replacement test, and B represents the replacement number taking a positive integer value; in the operation stage, the main lag position of the upstream node to the downstream node is estimated, for the directed edge u→d, the propagation strength, the significance and the main lag position are outputted; according to the propagation strength of the edge, an effective propagation path is screened, the effective propagation path is sorted to obtain a candidate node, the residual error of the candidate node is set to zero through virtual clipping, and forward propagation is performed through a semi-physical model, and a fault node is confirmed in the candidate node based on the forward propagation result; the virtual clipping comprises selecting the node ranked first in the root cause node ranking table as a target root cause, and taking out the out-edge set of the target root cause; without changing other parent sets and the operation stage, the residual error of the target root cause is artificially set to zero, the amplitude of the residual error of the downstream node is predicted through forward propagation, and a corresponding prediction curve is generated, for each downstream node, the prediction falling track is compared with the current residual error, and the prediction falling ratio is calculated.

2. The elevator fault diagnosis method of claim 1, wherein: The elevator operation data comprises traction system data, environment and load data, door machine system data and brake system data; the traction system data comprises current, DC bus voltage, car speed, car acceleration and motor output torque; the environment and load data comprises car load estimation value, car position floor information, environment temperature and humidity; the door machine system data comprises current curve, action duration and door position sensor signal of the opening and closing process of the door; the brake system data comprises brake coil on-off current, brake release and brake action time.

3. The elevator fault diagnosis method of claim 2, wherein: The operation stage is divided into six stages, namely, a starting acceleration stage, a uniform speed operation stage, a deceleration stage, a flat stage and a brake stage, an opening door stage and a closing door stage, wherein the starting acceleration stage, the uniform speed operation stage and the deceleration stage are traction-related operation stages.

4. The elevator fault diagnosis method of claim 3, wherein: The residual of the elevator operation data in the running phase includes, in the traction-related running phase, estimating the motor output torque expectation by simplifying the dynamic relationship, the motor output torque expectation being equal to the sum of the inertia demand torque, the viscous damping torque, the gravity equivalent torque and the friction torque, mapping the motor output torque expectation to the current expectation and the DC bus voltage expectation; In the leveling and braking phase, the on-off current expectation of the braking coil and the car speed expectation are constructed; In the opening and closing door phase, the action duration expectation and the current curve expectation of the opening and closing door process are generated based on the door machine system data; The residual of the elevator operation data is obtained by subtracting the corresponding expectation from the elevator operation data.

5. A method of diagnosing an elevator fault according to claim 4, characterized in that: The causal chain diagram reflecting the relationship between each component is established by fault mode analysis, the residual of the elevator operation data is taken as a node of the causal chain diagram, one node corresponds to one residual, the causal relationship between the nodes is determined based on the physical working principle of the elevator system, the directed edge is established in the direction from the upstream cause to the downstream result, and the establishment of the causal chain diagram is completed, wherein the node corresponding to the upstream cause is the upstream node, and the node corresponding to the downstream result is the downstream node.

6. A method of diagnosing an elevator fault according to claim 5, characterized in that: The candidate nodes are obtained by sorting the effective propagation paths, for each node in the effective propagation path, the out-edge set and the in-edge set are counted, the out-edge set is all downstream node edges pointed to by the node as an upstream, and the in-edge set is all edges pointed to it from other nodes as a downstream; A root cause score is defined for each node, the root cause score is composed of output contribution, input weakening and node residual energy, the output contribution is the sum of the propagation intensity of all out-edges of the node, the input weakening is the sum of the propagation intensity of all in-edges of the node, and the node residual energy is the mean square of the residual of the node in the running phase, and the root cause score is represented as the output contribution of the node minus the input weakening plus the node residual energy; The root cause scores of all nodes are calculated and sorted from high to low to form a root cause node sorting table.

7. An elevator fault diagnosis system applied to the elevator fault diagnosis method according to any one of claims 1 to 6, characterized by It includes, The acquisition module acquires the elevator operation data, divides the elevator operation process into running phases according to the elevator operation data, and calculates the residual of the elevator operation data in the running phase; The analysis module establishes a causal chain diagram reflecting the relationship between each component by fault mode analysis based on the elevator structure, and takes the direct upstream node set of the downstream node in the causal chain diagram as the parent set of the downstream node; The replacement module performs block replacement processing on the upstream node residual sequence of each edge in the causal chain diagram in the running phase to maintain the timing characteristics, generates a contrast residual sequence, and calculates the propagation intensity of the edge according to the contrast residual sequence; The positioning module filters the effective propagation path according to the propagation intensity of the edge, sorts the effective propagation path to obtain the candidate node, sets the candidate node residual to zero by virtual pinch-off, and performs forward propagation through a semi-physical model, and confirms the fault node in the candidate node based on the forward propagation result.

Images