Elevator safety performance maintenance cluster management system based on multi-source risk assessment

Abstract

The invention relates to the technical field of elevator maintenance management, in particular to an elevator safety performance maintenance cluster management system based on multi-source risk assessment, which comprises a visual cluster management center, a data acquisition unit, a risk assessment unit, a cluster evaluation unit, a collaborative task unit, an operation and maintenance matching unit and a feedback response unit, according to the method, the risk state of the elevator cluster is comprehensively described from the four dimensions of range-strength-association-linkage, meanwhile, the risk propagation rule is mined through the association diagram, the overall risk early warning accuracy of the cluster is improved, and the risk early warning accuracy is improved through risk-energy efficiency association analysis. According to the method, the elevator needing to be processed preferentially can be accurately locked through the risk level, the risk conduction strength and the unit energy consumption deviation degree, the maintenance economy can be verified through cost measurement and calculation, the dual goals of reducing the fault risk and reducing the energy consumption waste are finally achieved, operation and maintenance teams are reasonably arranged based on a task list, and the operation and maintenance efficiency is improved. And efficient clustered maintenance scheduling is realized.

Description

Technical Field

[0001] This invention relates to the field of elevator maintenance and management technology, and in particular to an elevator safety performance maintenance cluster management system based on multi-source risk assessment. Background Technology

[0002] In elevator clusters, some elevators form highly interconnected groups due to sharing power supply systems, control systems, or being in close physical locations. When one elevator in a highly interconnected group fails, the failure can easily spread to other elevators through various connections, triggering a chain reaction of failures and causing serious safety accidents and economic losses.

[0003] The existing elevator safety management system has the following shortcomings: the data collection dimension is limited, relying heavily on operating status parameters; the cluster management lacks correlation analysis, does not consider the mutual influence between elevators, risk warning is delayed, and maintenance scheduling relies on experience-based decisions, resulting in unreasonable resource allocation and low maintenance efficiency.

[0004] Especially in elevator cluster application scenarios such as large commercial complexes and high-rise residential communities, traditional management methods are difficult to cope with complex operating environments and diverse usage needs, and there is an urgent need for an intelligent and collaborative cluster management system.

[0005] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0006] The purpose of this invention is to provide an elevator safety performance maintenance cluster management system based on multi-source risk assessment to address the aforementioned technical deficiencies. This invention comprehensively characterizes the risk status of elevator clusters from four dimensions: scope, intensity, correlation, and chain reaction. Simultaneously, it mines risk propagation patterns through correlation diagrams, improving the overall risk warning accuracy of the cluster. Furthermore, through risk-energy efficiency correlation analysis, it can accurately identify elevators requiring priority handling based on risk level, risk transmission intensity, and unit energy consumption deviation. It can also verify the economic viability of maintenance through cost calculations, ultimately achieving the dual goals of "reducing failure risk" and "reducing energy waste." Finally, it enables efficient clustered maintenance scheduling by rationally arranging maintenance teams based on task lists.

[0007] The objective of this invention can be achieved through the following technical solution: an elevator safety performance maintenance cluster management system based on multi-source risk assessment, including a visual cluster management center, a data acquisition unit, a risk assessment unit, a cluster evaluation unit, a collaborative task unit, an operation and maintenance matching unit, and a feedback response unit;

[0008] The data acquisition unit is used to collect multi-source data during the operation of elevator cluster n (n≥2) and send it to the visual cluster management center for storage;

[0009] The risk assessment unit is used to process and analyze the collected multi-source data, and to discriminate the obtained risk level Fi (a natural number i > 0) to obtain risk elevators and conventional elevators.

[0010] The cluster assessment unit is used to perform cluster risk classification and feedback analysis on elevator clusters, and to process the obtained elevator cluster risk level JQ to obtain low-risk, medium-risk and high-risk signals.

[0011] The collaborative task unit is used to perform operation and maintenance task management and benefit verification analysis on the unit energy consumption deviation of the collected risk elevators, obtain a task list and cost savings, and at the same time, perform discrimination processing on the obtained cost savings to obtain expected benefit signals or low benefit signals.

[0012] The operations and maintenance matching unit is used to perform intelligent filtering and matching analysis on the task list, and set the matching team corresponding to the minimum value of the shortest route distance as the target operations and maintenance team.

[0013] Preferably, the multi-source data includes single-elevator operating parameters, cluster common environmental parameters, elevator group associated operating data, and historical cluster operation and maintenance records.

[0014] Preferably, the analysis process of the risk assessment unit is as follows:

[0015] S1: Preprocess the collected multi-source data to obtain initial multi-source data;

[0016] S2: The preprocessed initial multi-source data is integrated into a matrix R with unified dimensions. In matrix R, rows represent elevator numbers and columns represent standardized parameters and time series features.

[0017] S3: Obtain the risk transmission intensity Cij between elevator i (a natural number i > 0) and elevator j (a natural number j > 0) based on matrix R:

[0018] S4: Based on the matrix R input into the preset multi-source risk assessment model, the risk level Fi of elevator i is obtained.

[0019] Preferably, the analysis process of risk transmission intensity Cij is as follows: the distance Sij between elevator i and elevator j, the degree of overlap of the shared power supply or control system Eij, and the number of failures occurring in the same period are obtained. The preset weight coefficients a1, a2, and a3 corresponding to the distance Sij between the two nodes, the degree of overlap of the shared power supply or control system Eij, and the number of failures occurring in the same period Hij are obtained respectively. a1, a2, and a3 are all greater than zero.

[0020] Risk transmission intensity Cij = (1 - Sij / maximum distance in the cluster) × a1 + Eij × a2 + Hij × a3.

[0021] Preferably, the analysis process of the cluster evaluation unit is as follows:

[0022] Obtain the total number of risk elevators and set the ratio between the total number of risk elevators and n as the risk coverage CR;

[0023] The ratio between the sum of the risk levels corresponding to risk elevators and the total number of risk elevators is set as the risk intensity index SR.

[0024] The sum of the risk intensity index SR of all elevator pairs in the cluster with risk levels greater than the preset risk level threshold is obtained, and the theoretical maximum number of associated pairs between risky elevators in the elevator cluster is obtained. The ratio between the sum of the risk intensity index SR of all elevator pairs in the cluster with risk levels greater than the preset risk level threshold and the theoretical maximum number of associated pairs between risky elevators in the elevator cluster is set as the risk association density DR.

[0025] Construct a risk correlation graph, with elevators as nodes and edges representing risks with a transmission strength greater than a preset risk transmission strength;

[0026] The number of nodes in the longest connected component is obtained based on the risk association graph, and the number of nodes in the longest connected component is set as the risk chain length LR;

[0027] The risk level JQ of the elevator cluster is calculated by weighting the risk coverage CR, risk intensity index SR, risk association density DR, and risk chain length LR.

[0028] Retrieve the preset elevator cluster risk level range parameters: minimum value JQ, maximum value JQ, and perform discrimination processing on the elevator cluster risk level JQ to obtain low risk signal, medium risk signal and high risk signal;

[0029] Low-risk signals, medium-risk signals, and high-risk signals are collectively referred to as risk signals.

[0030] Preferably, the analysis process of the collaborative task unit is as follows:

[0031] The unit energy consumption deviation of the risk elevator is obtained (the ratio of the actual unit energy consumption of a single elevator to the average unit energy consumption of elevators of the same type or with the same service life, minus 1). At the same time, the risk level of the risk elevator is obtained, and the product of the unit energy consumption deviation and the risk level is set as the risk unit energy consumption ratio.

[0032] The system also performs a risk unit energy consumption ratio discrimination process, retains the risk elevators whose risk unit energy consumption ratio is greater than the preset risk unit energy consumption ratio threshold, and sets them as marked elevators.

[0033] Preferably, the risk transmission intensity of the marked elevators is obtained, and the elevators are sorted in descending order based on the risk transmission intensity. At the same time, a task list for each marked elevator is generated based on the sorted risk transmission intensity.

[0034] The cost savings of each marked elevator are obtained. Cost savings = (unit energy consumption before maintenance - unit energy consumption after maintenance) × average daily running time × electricity price × 365 days - maintenance investment cost. The cost savings are then processed to obtain the expected benefit signal or low benefit signal.

[0035] Preferably, the analysis process of the operation and maintenance matching unit is as follows:

[0036] Take the target elevator in the task list as the center and the radius as r kilometers. Set the area obtained by drawing a circle around the center as the retrieval area. Obtain the real-time status information, tool status information and material information of each maintenance team in the retrieval area. The real-time status information includes idle and busy, the tool status information includes available and unavailable, and the material information includes the model and quantity of the parts.

[0037] Available maintenance teams are filtered based on real-time status information. At the same time, maintenance teams that contain the professional tools required for the task and are in an available status are selected from the task list and set as candidate maintenance teams.

[0038] Based on the task list, the required parts model and quantity are obtained, and the required parts model and quantity are matched with the material information carried or available by the candidate maintenance team. Candidate maintenance teams whose parts model is the same as the required parts model and whose parts quantity is greater than the required quantity are retained and set as the matching team.

[0039] Obtain the shortest route distance between each matched team and the target elevator, and set the matched team corresponding to the minimum shortest route distance as the target maintenance team.

[0040] The beneficial effects of this invention are as follows:

[0041] (1) This invention can comprehensively acquire elevator operation information and historical data through multi-source data acquisition, providing sufficient basis for risk assessment, improving the comprehensiveness and accuracy of the assessment. The multi-source risk assessment model based on deep learning can effectively integrate different types of data features, accurately identify the safety risk level of the elevator, and provide targeted guidance for maintenance work.

[0042] (2) This invention comprehensively depicts the risk status of elevator clusters from four dimensions: scope, intensity, correlation, and chain. At the same time, it can realize the accurate conversion from cluster data to risk indicators, providing data support for the maintenance and scheduling of elevator clusters. Furthermore, by mining the risk propagation pattern through the correlation diagram, the accuracy of the overall risk warning of the cluster is improved. Moreover, through risk-energy efficiency correlation analysis, it can accurately identify the elevators that need to be prioritized for handling by risk level, risk transmission intensity, and unit energy consumption deviation. It can also verify the economic efficiency of maintenance through cost calculation, ultimately achieving the dual goals of "reducing failure risk" and "reducing energy waste".

[0043] (3) The present invention rationally arranges the operation and maintenance team based on the task list, that is, the risk assessment results (single ladder risk value, risk transmission intensity) are transformed into an executable maintenance task plan, and efficient clustered maintenance scheduling is achieved through priority sorting and resource matching. Attached Figure Description

[0044] The invention will now be further described with reference to the accompanying drawings;

[0045] Figure 1 This is a system flowchart of the present invention;

[0046] Figure 2 This is a partial reference diagram of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments;

[0049] Example 1:

[0050] Please see Figures 1 to 2 As shown, the present invention is an elevator safety performance maintenance cluster management system based on multi-source risk assessment, including a visual cluster management center, a data acquisition unit, a risk assessment unit, a cluster evaluation unit, a collaborative task unit, an operation and maintenance matching unit, and a feedback response unit.

[0051] The data acquisition unit has a one-way communication connection with the visual cluster management center. The visual cluster management center has a one-way communication connection with the risk assessment unit and the cluster evaluation unit. The risk assessment unit has a one-way communication connection with the collaborative task unit and the cluster evaluation unit. The collaborative task unit has a one-way communication connection with the operation and maintenance matching unit. The operation and maintenance matching unit and the cluster evaluation unit have a one-way communication connection with the feedback response unit.

[0052] The data acquisition unit is used to collect multi-source data during the operation of elevator cluster n (n≥2) and send it to the visual cluster management center for storage. The multi-source data includes single elevator operation parameters, cluster common environmental parameters, elevator group associated operation data, and historical cluster operation and maintenance records; where elevator cluster n represents the total number of elevators.

[0053] Single elevator operating parameters: such as operating speed, number of start-stop cycles, traction machine temperature, and other independent operating data for a single elevator;

[0054] Cluster common environmental parameters include: building power supply stability (voltage fluctuation frequency, power outage records), temperature and humidity of the shaft shared space (real-time monitoring values ​​and fluctuation range), and external vibration transmission data (such as the impact of surrounding construction and equipment resonance).

[0055] Elevator group operation data: concurrent operation frequency of elevators in the same building (number of times they run simultaneously per unit time), load complementarity data (load changes of other elevators when a certain elevator is fully loaded), and fault propagation records (abnormal responses of associated elevators after a single elevator failure).

[0056] Historical cluster operation and maintenance records: including information such as past fault types, repair duration, and replacement parts;

[0057] The risk assessment unit is used to process and analyze the collected multi-source data. The specific data processing and risk assessment analysis process is as follows:

[0058] S1: Preprocess the collected multi-source data to obtain initial multi-source data;

[0059] Preprocessing includes data cleaning, data integration, and data transformation. Data cleaning uses statistical outlier detection methods to remove noisy data, data integration merges data from different sources, and data transformation standardizes the data using the min-max standardization method.

[0060] S2: The preprocessed initial multi-source data is integrated into a matrix R with unified dimensions. In matrix R, rows represent elevator numbers and columns represent standardized parameters and time series features.

[0061] S3: Obtain the risk transmission intensity Cij between elevator i (a natural number i > 0) and elevator j (a natural number j > 0) based on matrix R:

[0062] Obtain the distance Sij between elevator i and elevator j, the degree of overlap of the shared power supply or control system Eij (if shared, the degree of overlap is 1; if partially shared, the degree of overlap is 0.5; if not shared, the degree of overlap is 0), and the number of failures occurring in the same period Hij. Obtain the preset weight coefficients a1, a2, and a3 corresponding to the distance Sij between the two nodes, the degree of overlap of the shared power supply or control system Eij, and the number of failures occurring in the same period Hij. a1, a2, and a3 are all greater than zero.

[0063] The risk transmission intensity Cij is obtained through weighted summation and calculation.

[0064] Wherein, the risk transmission intensity Cij = (1-Sij / maximum distance in the cluster) × a1 + Eij × a2 + Hij × a3;

[0065] S4: Based on the matrix R input into the preset multi-source risk assessment model, the risk level Fi of elevator i is obtained;

[0066] The risk level Fi is judged and processed. Elevators with a risk level Fi greater than the preset risk level threshold are set as risk elevators, and elevators with a risk level Fi less than or equal to the preset risk level threshold are set as normal elevators.

[0067] The feedback response unit is used to respond to risk elevators and regular elevators, and marks risk elevators with red and regular elevators with green to intuitively understand the status of each elevator;

[0068] The multi-source risk assessment model employs a deep learning-based fusion model, comprising a feature extraction layer, a feature fusion layer, and a risk assessment layer. The feature extraction layer uses a convolutional neural network to extract features from the initial multi-source data. The feature fusion layer uses an attention mechanism to weightedly fuse the extracted features. The risk assessment layer uses a fully connected neural network to output the elevator's safety risk assessment results.

[0069] This invention, through multi-source data acquisition, can comprehensively obtain elevator operation information and historical data, providing sufficient basis for risk assessment, improving the comprehensiveness and accuracy of the assessment. By adopting a multi-source risk assessment model based on deep learning, it can effectively integrate the characteristics of different types of data, accurately identify the safety risk level of the elevator, and provide targeted guidance for maintenance work.

[0070] Example 2:

[0071] The cluster assessment unit is used to perform cluster risk classification and feedback analysis on elevator clusters. The specific cluster risk classification and feedback analysis process is as follows:

[0072] Obtain the total number of risk elevators and set the ratio between the total number of risk elevators and n as the risk coverage CR;

[0073] At the same time, the ratio between the sum of the risk levels corresponding to the risk elevators and the total number of risk elevators is obtained, and the ratio between the sum of the risk levels corresponding to the risk elevators and the total number of risk elevators is set as the risk intensity index SR;

[0074] The sum of the risk intensity index SR of all elevator pairs in the cluster with risk levels greater than the preset risk level threshold is obtained, as well as the theoretical maximum number of associated pairs between risky elevators in the elevator cluster. The ratio between the sum of the risk intensity index SR of all elevator pairs in the cluster with risk levels greater than the preset risk level threshold and the theoretical maximum number of associated pairs between risky elevators in the elevator cluster is set as the risk association density DR (which measures the degree of association between high-risk elevators and reflects the basic conditions for risk diffusion).

[0075] Construct a risk correlation graph, with elevators as nodes and edges representing risks with a transmission strength greater than a preset risk transmission strength;

[0076] The number of nodes in the longest connected component is obtained based on the risk association graph, and the number of nodes in the longest connected component is set as the risk chain length LR;

[0077] The risk level JQ of the elevator cluster is calculated by weighting the risk coverage CR, risk intensity index SR, risk association density DR, and risk chain length LR.

[0078] Elevator cluster risk level JQ = risk coverage CR×v1 + risk intensity index SR×v2 + risk association density DR×v3 + risk chain length LR×v4, where v1, v2, v3 and v4 are all greater than zero;

[0079] Retrieve the preset elevator cluster risk level range parameters: minimum value JQ, maximum value JQ, and perform discrimination processing on the elevator cluster risk level JQ. If the elevator cluster risk level JQ < minimum value JQ, a low-risk signal is generated; if the minimum value JQ ≤ elevator cluster risk level JQ ≤ maximum value JQ, a medium-risk signal is generated; if the elevator cluster risk level JQ > maximum value JQ, a high-risk signal is generated.

[0080] Low-risk signals, medium-risk signals, and high-risk signals are collectively referred to as risk signals.

[0081] The feedback response unit is used to respond to risk signals and immediately display the preset warning text corresponding to the risk signal, so as to intuitively understand the risk situation of the elevator cluster.

[0082] This indicator system can comprehensively depict the risk status of elevator clusters from four dimensions: scope, intensity, correlation, and chain reaction. It can also achieve accurate conversion from cluster data to risk indicators, providing data support for the maintenance and scheduling of elevator clusters.

[0083] At the same time, it breaks through the limitations of independent assessment of a single ladder, and improves the accuracy of risk early warning for the entire cluster by mining the risk propagation pattern through the association diagram;

[0084] The collaborative task unit is used to perform operation and maintenance task management and benefit verification analysis on the unit energy consumption deviation of the collected risk elevators. The specific operation and maintenance task management and benefit verification analysis process is as follows:

[0085] The unit energy consumption deviation of the risk elevator is obtained (the ratio of the actual unit energy consumption of a single elevator to the average unit energy consumption of elevators of the same type or with the same service life, minus 1). At the same time, the risk level of the risk elevator is obtained, and the product of the unit energy consumption deviation and the risk level is set as the risk unit energy consumption ratio.

[0086] The risk unit energy consumption ratio is then processed to identify and retain the risk elevators whose risk unit energy consumption ratio is greater than the preset risk unit energy consumption ratio threshold, and these elevators are set as marked elevators.

[0087] The risk transmission intensity of the marked elevators is obtained, and they are sorted in descending order based on the risk transmission intensity. At the same time, a task list for each marked elevator is generated based on the sorted risk transmission intensity. The task list includes information such as task ID, target elevator, required employee skills, and estimated duration.

[0088] The system obtains the cost savings for each marked elevator. Cost savings = (unit energy consumption before maintenance - unit energy consumption after maintenance) × average daily operating time × electricity price × 365 days - maintenance cost. The system then processes the cost savings. If the cost savings are greater than or equal to a preset cost savings threshold, a expected benefit signal is generated; if the cost savings are less than the preset cost savings threshold, a low benefit signal is generated.

[0089] The feedback response unit is used to respond to expected benefit signals or low benefit signals, and immediately display the preset warning text corresponding to the expected benefit signals or low benefit signals, so as to intuitively understand whether the energy-saving economy of elevator maintenance meets the standards based on the feedback information, and then make rational decisions and adjustments to the elevator maintenance plan.

[0090] This invention uses "risk-energy efficiency correlation analysis" to accurately identify elevators that need priority handling by analyzing risk level, risk transmission intensity, and deviation of unit energy consumption. It also verifies the economics of maintenance through cost calculation, ultimately achieving the dual goals of "reducing failure risk" and "reducing energy waste".

[0091] The operations and maintenance matching unit is used to perform intelligent filtering and matching analysis on the task list. The specific intelligent filtering and matching analysis process is as follows:

[0092] Take the target elevator in the task list as the center and the radius as r kilometers. Set the area obtained by drawing a circle around the center as the retrieval area. Obtain the real-time status information, tool status information and material information of each maintenance team in the retrieval area. The real-time status information includes idle and busy, the tool status information includes available and unavailable, and the material information includes parts model, quantity, etc.

[0093] Available maintenance teams are filtered based on real-time status information. At the same time, maintenance teams that contain the professional tools required for the task (such as debuggers and multimeters) and whose status is "available" are obtained from the task list and set as candidate maintenance teams.

[0094] Based on the task list, the required parts model and quantity are obtained, and the required parts model and quantity are matched with the material information carried or available by the candidate maintenance team. Candidate maintenance teams whose parts model is the same as the required parts model and whose parts quantity is greater than the required quantity are retained and set as the matching team.

[0095] Obtain the shortest route distance between each matched team and the target elevator, and set the matched team corresponding to the minimum shortest route distance as the target maintenance team;

[0096] The feedback response unit is used to respond to the target operations and maintenance team, immediately display the target operations and maintenance team, and send the task list to the target operations and maintenance team.

[0097] This invention transforms risk assessment results (single-stack risk value, risk transmission intensity) into an executable maintenance task plan, and achieves efficient clustered maintenance scheduling through priority ranking and resource matching.

[0098] In summary, this invention, through multi-source data acquisition, can comprehensively obtain elevator operation information and historical data, providing sufficient basis for risk assessment and improving the comprehensiveness and accuracy of the assessment. Employing a deep learning-based multi-source risk assessment model, it can effectively integrate different types of data features, accurately identify the safety risk level of elevators, and provide targeted guidance for maintenance work. It comprehensively depicts the risk status of elevator clusters from four dimensions: scope, intensity, correlation, and interlocking. Simultaneously, it can achieve accurate conversion from cluster data to risk indicators, providing data support for elevator cluster maintenance scheduling. Furthermore, by mining risk propagation patterns through correlation graphs, it improves the overall risk warning accuracy of the cluster. Through risk-energy efficiency correlation analysis, it can accurately identify elevators requiring priority handling based on risk level, risk transmission intensity, and unit energy consumption deviation, and verify the economics of maintenance through cost calculation. Ultimately, it achieves the dual goals of "reducing failure risk" and "reducing energy waste." Finally, it rationally arranges the maintenance team based on a task list, transforming risk assessment results (single elevator risk value, risk transmission intensity) into an executable maintenance task plan. Through priority ranking and resource matching, it achieves efficient clustered maintenance scheduling.

[0099] The threshold is set for comparative analysis of results to determine whether they are good or bad. The value of the threshold is determined by a combination of large-scale model analysis of sample data and human experience. It can also be adjusted appropriately based on seasonal or common-sense influencing factors.

[0100] The size of the coefficient is a specific value obtained by quantifying each parameter to facilitate subsequent comparison. The size of the coefficient depends on the amount of sample data and the corresponding operating coefficient initially set by those skilled in the art for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value.

[0101] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An elevator safety performance maintenance cluster management system based on multi-source risk assessment, characterized in that, It includes a visual cluster management center, a data acquisition unit, a risk assessment unit, a cluster testing unit, a collaborative task unit, an operation and maintenance matching unit, and a feedback response unit; The data acquisition unit is used to collect multi-source data during the operation of elevator cluster n (n≥2) and send it to the visual cluster management center for storage; The risk assessment unit is used to process and analyze the collected multi-source data, and to discriminate the obtained risk level Fi (a natural number i > 0) to obtain risk elevators and conventional elevators. The cluster assessment unit is used to perform cluster risk classification and feedback analysis on elevator clusters, and to process the obtained elevator cluster risk level JQ to obtain low-risk, medium-risk and high-risk signals. The collaborative task unit is used to perform operation and maintenance task management and benefit verification analysis on the unit energy consumption deviation of the collected risk elevators, obtain a task list and cost savings, and at the same time, perform discrimination processing on the obtained cost savings to obtain expected benefit signals or low benefit signals. The operations and maintenance matching unit is used to perform intelligent filtering and matching analysis on the task list, and set the matching team corresponding to the minimum value of the shortest route distance as the target operations and maintenance team.

2. The elevator safety performance maintenance cluster management system based on multi-source risk assessment according to claim 1, characterized in that, The multi-source data includes single-elevator operating parameters, cluster common environmental parameters, elevator group associated operating data, and historical cluster operation and maintenance records.

3. The elevator safety performance maintenance cluster management system based on multi-source risk assessment according to claim 1, characterized in that, The analysis process of the risk assessment unit is as follows: S1: Preprocess the collected multi-source data to obtain initial multi-source data; S2: The preprocessed initial multi-source data is integrated into a matrix R with unified dimensions. In matrix R, rows represent elevator numbers and columns represent standardized parameters and time series features. S3: Obtain the risk transmission intensity Cij between elevator i (a natural number i > 0) and elevator j (a natural number j > 0) based on matrix R: S4: Based on the matrix R input into the preset multi-source risk assessment model, the risk level Fi of elevator i is obtained.

4. The elevator safety performance maintenance cluster management system based on multi-source risk assessment according to claim 3, characterized in that, Analysis process of risk transmission intensity Cij: The distance Sij between elevator i and elevator j, the degree of overlap of shared power supply or control system Eij, and the number of failures occurring in the same period Hij are obtained respectively. The preset weight coefficients a1, a2 and a3 corresponding to the distance Sij between the two nodes, the degree of overlap of shared power supply or control system Eij and the number of failures occurring in the same period Hij are obtained respectively. a1, a2 and a3 are all greater than zero. Risk transmission intensity Cij = (1 - Sij / maximum distance in the cluster) × a1 + Eij × a2 + Hij × a3.

5. The elevator safety performance maintenance cluster management system based on multi-source risk assessment according to claim 1, characterized in that, The analysis process of the cluster evaluation unit is as follows: Obtain the total number of risk elevators and set the ratio between the total number of risk elevators and n as the risk coverage CR; The ratio between the sum of the risk levels corresponding to risk elevators and the total number of risk elevators is set as the risk intensity index SR. The sum of the risk intensity index SR of all elevator pairs in the cluster with risk levels greater than the preset risk level threshold is obtained, and the theoretical maximum number of associated pairs between risky elevators in the elevator cluster is obtained. The ratio between the sum of the risk intensity index SR of all elevator pairs in the cluster with risk levels greater than the preset risk level threshold and the theoretical maximum number of associated pairs between risky elevators in the elevator cluster is set as the risk association density DR. Construct a risk correlation graph, with elevators as nodes and edges representing risks with a transmission strength greater than a preset risk transmission strength; The number of nodes in the longest connected component is obtained based on the risk association graph, and the number of nodes in the longest connected component is set as the risk chain length LR; The risk level JQ of the elevator cluster is calculated by weighting the risk coverage CR, risk intensity index SR, risk association density DR, and risk chain length LR. Retrieve the preset elevator cluster risk level range parameters: minimum value JQ, maximum value JQ, and perform discrimination processing on the elevator cluster risk level JQ to obtain low risk signal, medium risk signal and high risk signal; Low-risk signals, medium-risk signals, and high-risk signals are collectively referred to as risk signals.

6. The elevator safety performance maintenance cluster management system based on multi-source risk assessment according to claim 1, characterized in that, The analysis process of the collaborative task unit is as follows: The unit energy consumption deviation of the risk elevator is obtained (the ratio of the actual unit energy consumption of a single elevator to the average unit energy consumption of elevators of the same type or with the same service life, minus 1). At the same time, the risk level of the risk elevator is obtained, and the product of the unit energy consumption deviation and the risk level is set as the risk unit energy consumption ratio. The system also performs a risk unit energy consumption ratio discrimination process, retains the risk elevators whose risk unit energy consumption ratio is greater than the preset risk unit energy consumption ratio threshold, and sets them as marked elevators.

7. The elevator safety performance maintenance cluster management system based on multi-source risk assessment according to claim 6, characterized in that, The risk transmission intensity of the marked elevators is obtained, and the elevators are sorted in descending order based on the risk transmission intensity. At the same time, a task list for each marked elevator is generated based on the sorted risk transmission intensity. The cost savings of each marked elevator are obtained. Cost savings = (unit energy consumption before maintenance - unit energy consumption after maintenance) × average daily running time × electricity price × 365 days - maintenance investment cost. The cost savings are then processed to obtain the expected benefit signal or low benefit signal.

8. The elevator safety performance maintenance cluster management system based on multi-source risk assessment according to claim 1, characterized in that, The analysis process of the operation and maintenance matching unit is as follows: Take the target elevator in the task list as the center and the radius as r kilometers. Set the area obtained by drawing a circle around the center as the retrieval area. Obtain the real-time status information, tool status information and material information of each maintenance team in the retrieval area. The real-time status information includes idle and busy, the tool status information includes available and unavailable, and the material information includes the model and quantity of the parts. Available maintenance teams are filtered based on real-time status information. At the same time, maintenance teams that contain the professional tools required for the task and are in an available status are selected from the task list and set as candidate maintenance teams. Based on the task list, the required parts model and quantity are obtained, and the required parts model and quantity are matched with the material information carried or available by the candidate maintenance team. Candidate maintenance teams whose parts model is the same as the required parts model and whose parts quantity is greater than the required quantity are retained and set as the matching team. Obtain the shortest route distance between each matched team and the target elevator, and set the matched team corresponding to the minimum shortest route distance as the target maintenance team.

Images