Visual management system based on electromechanical industry data

Abstract

The invention discloses a visual management system based on electromechanical industry data, and relates to the technical field of train traction systems, and the system comprises a traction assembly modeling module, a working condition acquisition module, a heat effect identification module and a visual instruction module. The traction assembly modeling module identifies a train traction assembly, extracts the structure and operation parameters of the train traction assembly, and establishes a physical connection model; the working condition acquisition module acquires current, voltage, torque and temperature rise data under various typical working conditions, and constructs a working condition database. And the heat effect identification module constructs a heat accumulation curve based on the working condition data and the hot melting time constant, judges thermal inertia sudden change, cooling imbalance, critical overload and thermal collapse precursor risks, and generates corresponding multi-stage early warning instructions. And the visual instruction module dynamically displays the early warning level, marks the temperature rise trend, the heat rate change, the abnormal combination and the waste heat release time, and assists the train system in state evaluation and intelligent adjustment. Accurate monitoring and risk early warning of the thermal state of the electromechanical equipment are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of train traction systems, and in particular to a data visualization management system based on the electromechanical industry. Background Art

[0002] As the core drive unit for urban rail transit and heavy-haul railway trains, the traction system's operating status directly impacts the train's traction performance, safety margin, and equipment service life. Traction motors, reactors, and inverters, as key components of the traction system, are constantly exposed to high loads, variable operating conditions, and complex thermal environments. Without effective status assessment and early warning mechanisms, overheating, thermal imbalance, or accumulated overloads can easily lead to operational faults and even system failure.

[0003] Currently, in the electromechanical industry, especially in rail transit and high-intensity operating equipment, the operation monitoring and thermal status analysis of traction components mainly rely on decentralized sensor acquisition, regular inspections, and post-fault tracing. This presents the following prominent problems:

[0004] Discrete state identification and weak equipment modeling capabilities: Traditional operation and maintenance systems often monitor traction motors, reactors, and inverters separately, lacking a unified modeling and identification mechanism for the "traction component," a multi-device coupling unit. This makes it difficult to grasp the physical connections, operational linkages, and structural thermal inertia differences between devices at the system level, resulting in isolated equipment state judgment and a lack of a global perspective in analysis.

[0005] Single-minded thermal effect assessment and insufficient dynamic thermal risk identification capabilities: Traction equipment experiences significant heat accumulation and sudden temperature rises during highly variable operating conditions such as acceleration, climbing, and braking. Traditional thermal risk assessments rely heavily on determining if surface temperature exceeds a certain limit, ignoring the equipment's internal thermal inertia, melting time constant, and thermal coupling characteristics between different devices. This approach fails to fully and multidimensionally identify thermal imbalances, abnormal thermal rates, and critical thermal overloads, leading to delayed early warnings and blind spots in identifying thermal breakdowns.

[0006] Fragmented data utilization, invisible warnings, and unavailable strategies are prominent issues: Although some equipment has deployed sensors to monitor parameters such as temperature and current, the monitoring results have not formed a unified data structure and lack the support of a working condition database based on time synchronization and device hierarchical classification. Furthermore, most current warnings are still static threshold alarms, unable to dynamically respond based on multi-factor linkage, trend analysis, and thermal state evolution. Furthermore, the lack of visual expression makes it difficult to provide intuitive, real-time, and graphical auxiliary information for the operation and regulation system.

[0007] Therefore, there is an urgent need for a data visualization management system for the electromechanical industry that can integrate traction component modeling, operating condition extraction, thermal effect identification and multi-level visual warning functions. Summary of the Invention

[0008] In view of the deficiencies of the prior art, the present invention provides a data visualization management system based on the electromechanical industry to solve the problems mentioned in the background technology.

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a data visualization management system based on the electromechanical industry, comprising:

[0010] The traction component modeling module is used to identify and pair the jth traction component in the i-th train. The traction component consists of a traction motor, a reactor, and an inverter. The module extracts the structural parameters, operating level parameters, and thermal melting time constant of each device in the traction component and establishes a corresponding traction component model based on its physical connection relationship.

[0011] The operating condition collection module is used to collect historical operating condition data during the operation of the i-th train, including typical operating conditions such as acceleration, constant speed, climbing, braking, and regenerative braking. The module extracts the traction current, voltage, load torque, and surface temperature rise of the j-th traction component under each operating condition, and establishes an operating condition database for the j-th traction component.

[0012] The thermal effect identification module is used to construct a thermal accumulation curve based on the operating condition database of the jth traction component. The thermal accumulation curve constructs a thermal capacity index function based on the thermal melting time constant of its traction motor, reactor and inverter, and judges the following items:

[0013] If the growth rate dH(t) of the heat accumulation curve per unit time exceeds the first threshold Q1 of the set upper limit rate, it is determined that there is a risk of thermal inertia mutation in the j-th traction component, and a first-level warning instruction is generated;

[0014] If the thermal balance coefficient RPH between the traction motor and the inverter is lower than the second thermal imbalance threshold Q2 for N consecutive time steps, it is determined that the cooling balance state of the j-th traction component is abnormal and a second-level warning instruction is generated;

[0015] If the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t exceeds the third threshold Q3 and lasts for a time interval greater than Δt, it is determined that the j-th traction component has a thermal critical overload risk and a third-level warning instruction is generated;

[0016] If the following conditions are met simultaneously: dH(t)>Q1, RPH<thermal imbalance threshold Q2 for N consecutive time steps, RJ(t) corresponding to temperature rise at time t ≥ third threshold Q3, and the duration is greater than Δt time interval, then it is comprehensively judged that the j-th traction component has thermal collapse precursors, and the highest level warning instruction is generated;

[0017] The visual instruction module is used to generate a visual dynamic alarm map based on the warning instruction level of the j-th traction component, and to visually mark its operating status with thermal capacity consumption, including temperature rise trend, heat rate change, abnormal combination indication and residual heat release time estimation, to assist the train control system in status assessment and operation adjustment.

[0018] Preferably, the traction component modeling module includes a device identification unit and a parameter extraction unit:

[0019] The device identification unit is used to identify and pair the jth traction component in the i-th train, where the traction component consists of a traction motor, a reactor, and an inverter. The unit collects information including the device's unique number, installation location, cooling method, rated operating level, and traction circuit number by reading device coding information from the train's traction control system, scanning the device's QR code or radio frequency tag, and retrieving device maintenance records, thereby establishing a traction component identification table.

[0020] The parameter extraction unit is used to call the supporting equipment technical parameter documents and maintenance records according to the unique number of each device in the traction component identification table, extract the structural parameters, operating level parameters and thermal melting time constant of the traction motor, reactor and inverter, including: the rated power, rated speed, stator resistance, cooling type and thermal melting time constant of the traction motor; the rated current, equivalent inductance value, insulation level and thermal melting time constant of the reactor; the maximum bus voltage, switching frequency, IGBT module parameters and thermal melting time constant of the inverter; and form a comprehensive parameter set for the jth traction component.

[0021] Preferably, the traction component modeling module further includes a physical connection modeling unit:

[0022] The physical connection modeling unit establishes a physical connection relationship diagram of the traction motor, reactor, and inverter based on the traction component identification table and equipment parameters, combined with the train traction system electrical wiring diagram and layout topology, and numbers and colors the connection relationships to form a three-dimensional functional model of the traction component;

[0023] The specific steps of the 3D functional model of the traction components are as follows: based on the electrical wiring diagram and equipment installation layout diagram of the train traction system, the relative positions and connection relationships of the traction motor, reactor, and inverter in space are obtained to obtain the 2D layout data;

[0024] The two-dimensional layout data is converted into spatial coordinates and input into the three-dimensional modeling software of Autodesk Inventor, SolidWorks or Siemens, and modeled in combination with the physical connection relationship diagram of the traction motor, reactor and inverter to form a three-dimensional functional model of the traction component.

[0025] Preferably, the working condition acquisition module includes a working condition sensing unit, a data extraction unit and a working condition database construction unit;

[0026] The working condition sensing unit is used to collect the traction current value by deploying a current sensor at the traction motor input end and the inverter output side of the traction assembly of the i-th train; deploying a voltage sensor between the traction circuit DC bus and the AC output port to collect the traction voltage value; installing a torque sensor between the traction motor and the drive wheel system to collect the traction load torque; and installing a surface temperature sensor on the key hot surfaces of the traction motor, reactor and inverter housing to collect the surface temperature rise value of the equipment;

[0027] The data extraction unit is used to extract time period data corresponding to acceleration, constant speed, climbing, braking, and regenerative braking conditions based on the raw data collected by the working condition sensing unit, using the synchronization technology of the GPS clock and the train event recording system, and to classify and extract the traction current, voltage, load torque, and equipment surface temperature rise index of the jth traction component according to the working condition type;

[0028] The operating condition database construction unit is used to archive the extracted traction current, voltage, load torque and equipment surface temperature rise data according to five operating conditions: acceleration, constant speed, climbing, braking and regenerative braking, and establish a structured operating condition database with the jth traction component as the index unit.

[0029] Preferably, the thermal effect identification module includes a first calculation unit, a second calculation unit, a third calculation unit and an analysis unit;

[0030] The first calculation unit is used to extract the traction current, voltage, load torque and equipment surface temperature rise of the j-th traction component under various working conditions from the working condition database, and obtain the thermal melt index function H(t) after dimensionless processing by combining the thermal melt time constant and structural parameters of the traction motor, reactor and inverter extracted from the comprehensive parameter set of the j-th traction component.

[0031] Preferably, the second calculation unit is used to construct the thermal balance coefficient RPH by extracting the equipment surface temperature rise data of the traction motor and inverter in the j-th traction component and performing dimensionless processing.

[0032] Preferably, the third calculation unit is used to extract the traction data of each device in the j-th traction component under various working conditions, including the traction voltage value, traction load torque, traction equipment surface temperature rise and thermal melting time constant, and construct a heat accumulation rate function RJ(t) after dimensionless processing.

[0033] Preferably, the analysis unit is used to calculate the thermal melt index function H(t) at each synchronous time point t to form a set of ordered thermal accumulation points, plot them as a thermal accumulation curve in chronological order, and obtain the growth rate dH(t);

[0034] A first threshold value Q1 is preset in advance, and the growth rate dH(t) of the heat accumulation curve per unit time is compared and analyzed with the first threshold value Q1 to obtain a first evaluation result including:

[0035] If the growth rate of the heat accumulation curve per unit time dH(t) ≤ the first threshold Q1, it means that there is no risk of thermal inertia mutation for the j-th traction component and continuous monitoring is required;

[0036] If the growth rate of the heat accumulation curve per unit time dH(t) is greater than the first threshold Q1, it indicates that there is a risk of thermal inertia mutation in the jth traction component, and a first-level warning instruction is generated;

[0037] The second threshold Q2 is preset in advance, and the thermal balance coefficient RPH between the traction motor and the inverter is compared and analyzed with the second threshold Q2 to obtain the second evaluation result, including:

[0038] If the thermal balance coefficient RPH between the traction motor and the inverter is ≥ the thermal imbalance threshold Q2 in any of the N consecutive time steps, the cooling balance state of the traction component of the jth traction component is determined to be normal and is continuously monitored;

[0039] If the thermal balance coefficient RPH between the traction motor and the inverter is less than the thermal imbalance threshold Q2 for N consecutive time steps, it is determined that the cooling balance state of the j-th traction component is abnormal, and a second-level warning instruction is generated;

[0040] Extracting a preset third threshold Q3 and comparing and analyzing the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t with the third threshold Q3 to obtain a third evaluation result includes:

[0041] If the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t is less than the third threshold Q3, it is determined that there is no risk of thermal critical overload of the traction component and continuous monitoring is performed;

[0042] If the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t is greater than or equal to the third threshold Q3 and the duration is greater than the time interval Δt, it is determined that the traction component has a risk of thermal critical overload and a third-level warning instruction is generated.

[0043] Preferably, the thermal effect identification module further includes a comprehensive analysis unit:

[0044] The comprehensive analysis unit is used to comprehensively judge that the j-th traction component has a precursor to thermal collapse if the following conditions are simultaneously met: the growth rate dH(t) of the heat accumulation curve per unit time is greater than the first threshold Q1, the thermal balance coefficient RPH between the traction motor and the inverter is less than the thermal imbalance threshold Q2 in N consecutive time steps, the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t is greater than or equal to the third threshold Q3, and the duration is greater than the Δt time interval, and then generate the highest level warning instruction.

[0045] Preferably, the visual instruction module includes a visual dynamic alarm graph generation unit, a heat capacity consumption state standard unit and an auxiliary strategy unit;

[0046] The visual dynamic warning map generation unit is used to generate a warning instruction level for the j-th traction component based on the thermal effect recognition module. Each warning level corresponds to an independent layer and is dynamically refreshed according to the time dimension, including: a heat accumulation curve trajectory, a heat balance coefficient fluctuation diagram, a temperature rise change curve, and a real-time slope vector of the heat rate slope;

[0047] The heat capacity consumption state standard unit is used to visually mark the heat capacity consumption of the operating state of the j-th traction component, including:

[0048] Temperature rise trend annotation: visualize the surface temperature rise trend of the traction motor, reactor and inverter on a graph, and mark the key temperature rise inflection points, temperature rise continuous sections and the color level corresponding to the current temperature rise level;

[0049] Heat rate change annotation: Based on the change of the heat capacity exponential function over time, the growth rate mutation point and its corresponding time period are marked in the heat accumulation curve to form a slope change map to intuitively identify whether there is a stage-by-stage acceleration or abnormal sudden increase in the heat accumulation rate;

[0050] Abnormal combination indication labeling: Abnormal combinations of thermal inertia mutation, cooling imbalance, thermal critical overload, and thermal collapse precursors are superimposed on the corresponding equipment layer in the form of graphical labels, forming a multi-level abnormal state joint indication to assist in locating the source and severity of the abnormality;

[0051] Residual heat release time estimation: Based on the residual heat release time results provided by the evaluation module, the cooling time required is displayed in the form of a time scale below the graph. A color gradient bar indicates whether effective cooling can be completed before the next heavy load condition occurs, helping to determine whether the system can continue to operate under the current condition.

[0052] The auxiliary strategy unit is used to generate operation adjustment suggestions according to the warning level, specifically including:

[0053] Level 1 warning command prompts the cooling system to adjust, appropriately reduce the load, reduce the operating power by 5% to 10%, and start the air cooling or liquid cooling system;

[0054] Secondary warning command automatically activates the cooling system fault diagnosis module and reduces the traction pulse duty cycle to within 5%;

[0055] Level 3 warning command, forced load reduction operation, execution of maximum thermal protection limit action, traction power reduction by 15%, forced activation of emergency cooling program, and limitation of continuous operation time;

[0056] The highest level warning command activates interlock protection, stops inverter output, uploads fault instructions to the control center, and recommends emergency maintenance.

[0057] The present invention provides a data visualization management system based on the electromechanical industry. It has the following beneficial effects:

[0058] (1) This data visualization management system based on the electromechanical industry uses the equipment identification, parameter extraction, and physical connection modeling units in the traction component modeling module to automatically identify the traction component structure based on the train control system information. Combined with key parameters such as the thermal melt time constant, it constructs a three-dimensional functional model with complete electrical connection and thermal characteristic descriptions. This model not only has structural logical integrity, but also provides high-precision data support for subsequent operating condition analysis and thermal characteristic identification, significantly improving the automation level and accuracy of the digital modeling of the traction system.

[0059] (2) This system is based on the data visualization management system of the electromechanical industry. It collects the train operation data under typical operating conditions such as acceleration, constant speed, climbing, braking and regenerative braking through the working condition acquisition module. It combines GPS time synchronization with the event recording system to achieve precise alignment. It also archives the index data of each traction component according to the working condition classification and constructs a structured working condition database. This database provides a stable data foundation for subsequent thermal effect identification, solves the problem of thermal analysis lacking working condition subdivision and time series accuracy in traditional systems, and improves the pertinence and credibility of thermal assessment.

[0060] (3) This is a data visualization management system based on the electromechanical industry. It introduces three key indicators: the thermal melt index function, the thermal balance coefficient, and the heat accumulation rate function. A multi-level thermal effect assessment mechanism is designed to identify thermal risk situations such as thermal inertia mutation, cooling balance anomaly, thermal critical overload, and thermal collapse precursors. It also generates graded warning instructions by setting multiple thresholds and time-based continuous judgment criteria. This technology significantly improves the accuracy and response capability of traction component thermal risk identification, achieving a leap from conventional thermal protection to predictive thermal management.

[0061] (4) This is a data visualization management system based on the electromechanical industry. It uses a visualization instruction module to construct a multi-layer dynamic map containing heat accumulation trajectory, temperature rise trend, thermal rate mutation and abnormal combination indications, and provides real-time operation adjustment suggestions in combination with the warning level to assist the train system in thermal state perception and autonomous control. In particular, the residual heat release time estimation and cooling completion judgment mechanism can intuitively present the cooling capacity and the time conflict of the next working condition in the map, effectively supporting continuous operation decision-making and improving the thermal safety and intelligent response capability of the system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a block diagram and flow chart of the data visualization management system based on the electromechanical industry of the present invention. DETAILED DESCRIPTION

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0064] Example 1

[0065] See also Figure 1 The present invention provides a data visualization management system based on the electromechanical industry, including:

[0066] The traction component modeling module is used to identify and pair the jth traction component in the i-th train. The traction component consists of a traction motor, a reactor, and an inverter. The module extracts the structural parameters, operating level parameters, and thermal melting time constant of each device in the traction component and establishes a corresponding traction component model based on its physical connection relationship.

[0067] The operating condition collection module is used to collect historical operating condition data during the operation of the i-th train, including typical operating conditions such as acceleration, constant speed, climbing, braking, and regenerative braking. The module extracts the traction current, voltage, load torque, and surface temperature rise of the j-th traction component under each operating condition, and establishes an operating condition database for the j-th traction component.

[0068] The thermal effect identification module is used to construct a thermal accumulation curve based on the operating condition database of the jth traction component. The thermal accumulation curve constructs a thermal capacity index function based on the thermal melting time constant of its traction motor, reactor and inverter, and judges the following items:

[0069] If the growth rate dH(t) of the heat accumulation curve per unit time exceeds the first threshold Q1 of the set upper limit rate, it is determined that there is a risk of thermal inertia mutation in the j-th traction component, and a first-level warning instruction is generated;

[0070] If the thermal balance coefficient RPH between the traction motor and the inverter is lower than the second thermal imbalance threshold Q2 for N consecutive time steps, it is determined that the cooling balance state of the j-th traction component is abnormal and a second-level warning instruction is generated;

[0071] If the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t exceeds the third threshold Q3 and lasts for a time interval greater than Δt, it is determined that the j-th traction component has a thermal critical overload risk and a third-level warning instruction is generated;

[0072] If the following conditions are met simultaneously: dH(t)>Q1, RPH<thermal imbalance threshold Q2 for N consecutive time steps, RJ(t) corresponding to temperature rise at time t ≥ third threshold Q3, and the duration is greater than Δt time interval, then it is comprehensively judged that the j-th traction component has thermal collapse precursors, and the highest level warning instruction is generated;

[0073] The visual instruction module is used to generate a visual dynamic alarm map based on the warning instruction level of the j-th traction component, and to visually mark its operating status with thermal capacity consumption, including temperature rise trend, heat rate change, abnormal combination indication and residual heat release time estimation, to assist the train control system in status assessment and operation adjustment.

[0074] In this embodiment, through the modular design of traction component modeling, working condition collection, thermal effect identification and visualization instruction linkage, real-time identification and multi-level warning of the thermal dynamic behavior of the traction components in the train during operation can be achieved. In particular, through the joint judgment mechanism of the heat capacity index function, the thermal balance coefficient and the heat accumulation rate function, not only can different types of thermal anomalies such as thermal inertia mutation, cooling imbalance and critical overload be accurately identified, but the highest level of warning can also be issued before the precursors of thermal collapse appear, effectively improving the safety of the train traction system and the intelligent level of operation and control.

[0075] Example 2

[0076] This embodiment is explained in Example 1, please refer to Figure 1 Specifically, the traction component modeling module includes a device identification unit and a parameter extraction unit:

[0077] The device identification unit is used to identify and pair the jth traction component in the i-th train, where the traction component consists of a traction motor, a reactor, and an inverter. The unit collects information including the device's unique number, installation location, cooling method, rated operating level, and traction circuit number by reading device coding information from the train's traction control system, scanning the device's QR code or radio frequency tag, and retrieving device maintenance records, thereby establishing a traction component identification table.

[0078] The parameter extraction unit is used to call the supporting equipment technical parameter documents and maintenance records according to the unique number of each device in the traction component identification table, extract the structural parameters, operating level parameters and thermal melting time constant of the traction motor, reactor and inverter, including: the rated power, rated speed, stator resistance, cooling type and thermal melting time constant of the traction motor; the rated current, equivalent inductance value, insulation level and thermal melting time constant of the reactor; the maximum bus voltage, switching frequency, IGBT module parameters and thermal melting time constant of the inverter; and form a comprehensive parameter set for the jth traction component.

[0079] In this embodiment, by setting up a device identification unit and a parameter extraction unit, it is possible to accurately identify each traction component in the train and obtain structural-level parameters. In particular, by associating the device's unique number with multi-source information such as device coding information, QR code, radio frequency tag, and maintenance records, the structural parameters, operating level, and thermal melt time constant of the traction motor, reactor, and inverter can be fully extracted, providing high-precision basic data support for subsequent thermal model construction and thermal effect analysis, significantly improving the accuracy and customized analysis capabilities of the traction system's thermal management.

[0080] Example 3

[0081] This embodiment is explained in Example 2, please refer to Figure 1 Specifically, the traction component modeling module further includes a physical connection modeling unit:

[0082] The physical connection modeling unit establishes a physical connection relationship diagram of the traction motor, reactor, and inverter based on the traction component identification table and equipment parameters, combined with the train traction system electrical wiring diagram and layout topology, and numbers and colors the connection relationships to form a three-dimensional functional model of the traction component;

[0083] The specific steps of the 3D functional model of the traction components are as follows: based on the electrical wiring diagram and equipment installation layout diagram of the train traction system, the relative positions and connection relationships of the traction motor, reactor, and inverter in space are obtained to obtain the 2D layout data;

[0084] The two-dimensional layout data is converted into spatial coordinates and input into the three-dimensional modeling software of Autodesk Inventor, SolidWorks or Siemens, and modeled in combination with the physical connection relationship diagram of the traction motor, reactor and inverter to form a three-dimensional functional model of the traction component.

[0085] In this embodiment, by setting up a physical connection modeling unit, the spatial connection relationship between the traction motor, reactor and inverter can be automatically established and a three-dimensional functional model can be generated based on the electrical wiring diagram and equipment layout topology. This not only improves the intuitiveness and structural restoration of the traction component modeling, but also facilitates the provision of accurate spatial reference and connection logic basis in subsequent heat flow path analysis, spatial heat dissipation simulation and fault visualization diagnosis, thereby significantly improving the operability and visualization level of system-level thermal management and operation status analysis.

[0086] Example 4

[0087] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically, the working condition acquisition module includes a working condition ,sensing unit, a data extraction unit and a working condition database ,construction unit;

[0088] The working condition sensing unit is used to collect the traction current value by deploying a current sensor at the traction motor input end and the inverter output side of the traction assembly of the i-th train; deploying a voltage sensor between the traction circuit DC bus and the AC output port to collect the traction voltage value; installing a torque sensor between the traction motor and the drive wheel system to collect the traction load torque; and installing a surface temperature sensor on the key hot surfaces of the traction motor, reactor and inverter housing to collect the surface temperature rise value of the equipment;

[0089] The data extraction unit is used to extract time period data corresponding to acceleration, constant speed, climbing, braking, and regenerative braking conditions based on the raw data collected by the working condition sensing unit, using the synchronization technology of the GPS clock and the train event recording system, and to classify and extract the traction current, voltage, load torque, and equipment surface temperature rise index of the jth traction component according to the working condition type;

[0090] The operating condition database construction unit is used to archive the extracted traction current, voltage, load torque and equipment surface temperature rise data according to five operating conditions: acceleration, constant speed, climbing, braking and regenerative braking, and establish a structured operating condition database with the jth traction component as the index unit.

[0091] In this embodiment, by setting the working condition sensing unit, data extraction unit and working condition database construction unit in the working condition acquisition module, it is possible to achieve accurate collection, time synchronization and classified archiving of key parameters in the operation process of the traction component under multiple typical working conditions, and establish a structured working condition database for unit components. This not only improves the integrity and traceability of the operating status information of the traction component, but also provides high-quality, working condition-comparable data support for subsequent thermal effect analysis, operation risk judgment and strategy regulation, thereby significantly enhancing the system's response capability to changes in thermal behavior under different operating scenarios and the level of refined management.

[0092] Example 5

[0093] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically, the thermal effect identification module includes a first calculation unit, a second calculation unit, a third calculation unit and an analysis unit;

[0094] The first calculation unit is used to extract the traction current, voltage, load torque and equipment surface temperature rise of the j-th traction component under various working conditions from the working condition database, and obtain the thermal melt index function H(t) after dimensionless processing by combining the thermal melt time constant and structural parameters of the traction motor, reactor and inverter extracted from the comprehensive parameter set of the j-th traction component. The formula is as follows:

[0095] Where, I b (t) represents the traction current value of the bth device of the jth traction component at time t, R b represents the stator resistance value of the bth device of the jth traction component, τ b represents the thermal melting time constant of the bth device in the jth traction assembly, and e represents the base of the natural constant.

[0096] In this embodiment, by setting the first calculation unit in the thermal effect identification module, the current, voltage, load torque and equipment temperature rise data extracted from the traction component working condition database are used, combined with the thermal melt time constant and structural parameters in the comprehensive parameter set, dimensionless processing is performed and a thermal melt index function is constructed. This can achieve unified quantification and comparative analysis of the heat accumulation trends of different equipment under complex working conditions, significantly improve the recognition accuracy of the thermal inertia response characteristics of traction motors, reactors and inverters, and provide an accurate calculation basis and physical consistency guarantee for the scientific setting of subsequent thermal risk criteria and multi-level early warning.

[0097] Example 6

[0098] This embodiment is explained in Example 5, please refer to Figure 1Specifically, the second calculation unit is used to extract the surface temperature rise data of the traction motor and inverter in the j-th traction component, and construct the thermal balance coefficient RPH after dimensionless processing. The formula is as follows:

[0099] Where Tinv(t) represents the surface temperature rise of the inverter device in the j-th traction assembly at time t, and Tmotor(t) represents the surface temperature rise of the traction motor device in the j-th traction assembly at time t.

[0100] In this embodiment, by setting the second calculation unit in the thermal effect identification module, the surface temperature rise data of the traction motor and inverter in the j-th traction component are extracted and dimensionlessly converted to construct the thermal balance coefficient RPH. This can not only reflect the thermal coupling and cooling equilibrium status of the two types of key equipment during operation in real time, but also quickly identify potential faults such as decreased cooling efficiency or abnormal heat flow distribution under multiple working conditions, significantly improving the system's sensitive detection and prediction capabilities for thermal imbalance phenomena in traction components, and providing an accurate basis for graded warning and operation and maintenance intervention.

[0101] Example 7

[0102] This embodiment is explained in Example 5, please refer to Figure 1 Specifically, the third calculation unit is used to extract the traction data of each device in the j-th traction assembly under various working conditions, including the traction voltage value, traction load torque, traction device surface temperature rise, and thermal melting time constant, and construct a heat accumulation rate function RJ(t) after dimensionless processing. The formula is as follows:

[0103] Where U b (t) represents the traction voltage value of the bth device in the jth traction component at time t, M b (t) represents the traction load torque of the bth device in the jth traction assembly at time t, T b (t) represents the surface temperature rise of the bth device in the jth traction assembly at time t, τ b Indicates the melting time constant.

[0104] In this embodiment, by setting the third calculation unit in the thermal effect identification module, the traction voltage, load torque, equipment surface temperature rise and thermal melting time constant of each device in the j-th traction component under different working conditions are extracted, and the heat accumulation rate function is constructed after dimensionless processing. This can not only dynamically evaluate the cumulative trend of heat load with changes in working conditions, but also accurately identify the key critical points in the thermal stress superposition process, thereby effectively judging whether the equipment has thermal overload or thermal fatigue risks, and significantly enhancing the thermal safety monitoring and risk warning capabilities of the traction system under complex working conditions.

[0105] Example 8

[0106] This embodiment is explained in Example 5, please refer to Figure 1 Specifically, the analysis unit is used to calculate the thermal melt index function H(t) at each synchronous time point t to form a set of ordered thermal accumulation points, draw them into a thermal accumulation curve in chronological order, and obtain the growth rate dH(t);

[0107] A first threshold value Q1 is preset in advance, and the growth rate dH(t) of the heat accumulation curve per unit time is compared and analyzed with the first threshold value Q1 to obtain a first evaluation result including:

[0108] If the growth rate of the heat accumulation curve per unit time dH(t) ≤ the first threshold Q1, it means that there is no risk of thermal inertia mutation for the j-th traction component and continuous monitoring is required;

[0109] If the growth rate of the heat accumulation curve per unit time dH(t) is greater than the first threshold Q1, it indicates that there is a risk of thermal inertia mutation in the jth traction component, and a first-level warning instruction is generated;

[0110] The second threshold Q2 is preset in advance, and the thermal balance coefficient RPH between the traction motor and the inverter is compared and analyzed with the second threshold Q2 to obtain the second evaluation result, including:

[0111] If the thermal balance coefficient RPH between the traction motor and the inverter is ≥ the thermal imbalance threshold Q2 in any of the N consecutive time steps, the cooling balance state of the traction component of the jth traction component is determined to be normal and is continuously monitored;

[0112] If the thermal balance coefficient RPH between the traction motor and the inverter is less than the thermal imbalance threshold Q2 for N consecutive time steps, it is determined that the cooling balance state of the j-th traction component is abnormal, and a second-level warning instruction is generated;

[0113] Extracting a preset third threshold Q3 and comparing and analyzing the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t with the third threshold Q3 to obtain a third evaluation result includes:

[0114] If the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t is less than the third threshold Q3, it is determined that there is no risk of thermal critical overload of the traction component and continuous monitoring is performed;

[0115] If the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t is greater than or equal to the third threshold Q3 and the duration is greater than the time interval Δt, it is determined that the traction component has a risk of thermal critical overload and a third-level warning instruction is generated.

[0116] The first threshold Q1 is determined by collecting and statistically analyzing data on the heat accumulation behavior of a large number of traction systems under typical operating conditions, such as acceleration, hill climbing, and regenerative braking. The actual distribution characteristics of the growth rate per unit time of the heat accumulation curve are extracted, and the numerical ranges of the thermal inertia mutation points under normal and abnormal conditions for different equipment types are identified. This threshold Q1 is determined by combining design parameters such as the traction equipment's heat capacity structure, cooling method, and allowable temperature rise rate, with reference to the thermal response standards for traction motors, reactors, and inverters, as well as thermal management performance indicators provided by equipment manufacturers. This threshold Q1 is determined based on expert experience to accurately reflect the traction component's sensitivity to rapid heat accumulation, thereby enabling early identification and early warning of thermal inertia mutation risks.

[0117] The second threshold Q2 is obtained by analyzing the ratio characteristics of the surface temperature rise trends of the traction motor and inverter equipment in a large amount of traction system operation data. The variation pattern of the thermal balance coefficient RPH in the thermal equilibrium state and thermal imbalance state is extracted. The stability range and fluctuation threshold of RPH in continuous time steps are statistically analyzed. In addition, the thermal conductivity efficiency, operating redundancy tolerance and transient temperature difference response capability of different types of cooling structures are combined with reference to the traction system thermal management specifications, equipment thermal coupling response test data and the control system allowable thermal difference index. A reasonable thermal imbalance judgment threshold Q2 is formulated. This threshold is used to identify thermal imbalance phenomena caused by cooling system efficiency degradation or local heat accumulation, thereby triggering the adjustment or early warning mechanism in a timely manner.

[0118] The third threshold value Q3 is obtained in the following way: Based on the surface temperature rise records and duration distribution of the traction motor, reactor and inverter during operation under various working conditions, the temperature rise amplitude range of the equipment under stable operation, overload operation and critical thermal failure boundary is extracted. Combined with the thermal melting time constant and its dynamic change trend, an extreme characteristic model of heat accumulation for different equipment is established. Referring to the relevant rail transit traction system thermal design specifications, the allowable temperature rise limits given by equipment manufacturers, the thermal degradation critical points of IGBT modules and motor insulation systems, and the empirical judgment of industry experts on the temperature rise evolution behavior before thermal failure, a temperature rise threshold Q3 for identifying thermal critical overload risks is formulated. This threshold ensures that the system can provide timely warnings before the temperature rise exceeds the safety boundary, thereby ensuring the thermal safety of the equipment and the reliability of the system operation.

[0119] In this embodiment, by incorporating an analysis unit within the thermal effect identification module, and relying on an ordered sequence of thermal parameters formed by the melt index function, the thermal balance coefficient, and the heat accumulation rate function under a unified time reference, combined with three preset risk thresholds Q1, Q2, and Q3 and a time duration condition Δt, it is possible to implement graded assessment and dynamic early warning for three types of risks: sudden thermal inertia changes, cooling balance anomalies, and critical thermal overloads in traction components. This approach can proactively detect the evolution of thermal behavior before a device physically fails, triggering graded early warning commands and providing feedforward regulation signals to the train control system, significantly improving the operational safety and intelligent thermal management of the train traction system.

[0120] Example 9

[0121] This embodiment is explained in Example 5, please refer to Figure 1 Specifically, the thermal effect identification module further includes a comprehensive analysis unit:

[0122] The comprehensive analysis unit is used to comprehensively judge that the j-th traction component has a precursor to thermal collapse if the following conditions are simultaneously met: the growth rate dH(t) of the heat accumulation curve per unit time is greater than the first threshold Q1, the thermal balance coefficient RPH between the traction motor and the inverter is less than the thermal imbalance threshold Q2 in N consecutive time steps, the temperature rise value corresponding to the heat accumulation rate function RJ(t) at time t is greater than or equal to the third threshold Q3, and the duration is greater than the Δt time interval, and then generate the highest level warning instruction.

[0123] In this embodiment, by setting up the comprehensive analysis unit, when the growth rate of the heat accumulation curve per unit time exceeds the first threshold Q1, and the thermal balance coefficient RPH between the traction motor and the inverter is lower than the thermal imbalance threshold Q2 in N consecutive time steps, and the temperature rise value of the heat accumulation rate function at time t reaches or exceeds the third threshold Q3 and lasts for more than the Δt time interval, it is comprehensively judged that the current traction component has entered the thermal collapse precursor state, and the highest level warning instruction is generated in time; this solution realizes the accurate identification and early intervention of the thermal runaway risk of the traction system through multi-indicator coupling judgment and dynamic trend linkage monitoring, significantly improving the system's response capability and safety assurance level to extreme thermal risks, and effectively avoiding equipment damage and traction interruption accidents caused by thermal collapse.

[0124] Example 10

[0125] This embodiment is explained in Example 9, please refer to Figure 1 ,Specifically, the visual instruction module includes a visual dynamic alarm map generation unit, a ,heat capacity consumption state standard unit and an auxiliary strategy unit;

[0126] The visual dynamic warning map generation unit is used to generate a warning instruction level for the j-th traction component based on the thermal effect recognition module. Each warning level corresponds to an independent layer and is dynamically refreshed according to the time dimension, including: a heat accumulation curve trajectory, a heat balance coefficient fluctuation diagram, a temperature rise change curve, and a real-time slope vector of the heat rate slope;

[0127] The heat capacity consumption state standard unit is used to visually mark the heat capacity consumption of the operating state of the j-th traction component, including:

[0128] Temperature rise trend annotation: visualize the surface temperature rise trend of the traction motor, reactor and inverter on a graph, and mark the key temperature rise inflection points, temperature rise continuous sections and the color level corresponding to the current temperature rise level;

[0129] Heat rate change annotation: Based on the change of the heat capacity exponential function over time, the growth rate mutation point and its corresponding time period are marked in the heat accumulation curve to form a slope change map to intuitively identify whether there is a stage-by-stage acceleration or abnormal sudden increase in the heat accumulation rate;

[0130] Abnormal combination indication labeling: Abnormal combinations of thermal inertia mutation, cooling imbalance, thermal critical overload, and thermal collapse precursors are superimposed on the corresponding equipment layer in the form of graphical labels, forming a multi-level abnormal state joint indication to assist in locating the source and severity of the abnormality;

[0131] Residual heat release time estimation: Based on the residual heat release time results provided by the evaluation module, the cooling time required is displayed in the form of a time scale below the graph. A color gradient bar indicates whether effective cooling can be completed before the next heavy load condition occurs, helping to determine whether the system can continue to operate under the current condition.

[0132] The auxiliary strategy unit is used to generate operation adjustment suggestions according to the warning level, specifically including:

[0133] Level 1 warning command prompts the cooling system to adjust, appropriately reduce the load, reduce the operating power by 5% to 10%, and start the air cooling or liquid cooling system;

[0134] Secondary warning command automatically activates the cooling system fault diagnosis module and reduces the traction pulse duty cycle to within 5%;

[0135] Level 3 warning command, forced load reduction operation, execution of maximum thermal protection limit action, traction power reduction by 15%, forced activation of emergency cooling program, and limitation of continuous operation time;

[0136] The highest level warning command activates interlock protection, stops inverter output, uploads fault instructions to the control center, and recommends emergency maintenance.

[0137] In this embodiment, by setting the visualization instruction module, a dynamic multi-layer visualization alarm map is constructed based on the multi-level warning results generated by the thermal effect identification module, and key thermal effect indicators such as heat accumulation trajectory, thermal balance fluctuation, temperature rise trend and rate slope change are intuitively presented in the form of time series; through multi-dimensional visualization annotation methods such as temperature rise trend, thermal rate change, abnormal combination state and residual heat release time, a detailed expression of the thermal state of the traction component and real-time perception of abnormal changes are achieved; combined with the auxiliary strategy unit, operation adjustment suggestions are automatically generated according to different warning levels, from mild load reduction to forced power limitation to shutdown interlock protection, forming a complete alarm response and intervention closed loop; this solution effectively enhances the intuitive expression of thermal risk status and the execution efficiency of control response, improves the accuracy of operation and maintenance personnel in identifying the traction thermal state and the efficiency of disposal decision-making, and significantly improves the operational safety and intelligent management and control level of the traction system.

[0138] The threshold value is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

Claims

1. A data visualization management system based on the electromechanical industry, characterized by: include: The traction component modeling module is used to identify and pair the jth traction component in the i-th train. The traction component consists of a traction motor, a reactor, and an inverter. The module extracts the structural parameters, operating level parameters, and thermal melting time constant of each device in the traction component and establishes a corresponding traction component model based on its physical connection relationship. The operating condition collection module is used to collect historical operating condition data during the operation of the i-th train, including typical operating conditions such as acceleration, constant speed, climbing, braking, and regenerative braking. The module extracts the traction current, voltage, load torque, and surface temperature rise of the j-th traction component under each operating condition, and establishes an operating condition database for the j-th traction component. The thermal effect identification module is used to construct a thermal accumulation curve based on the operating condition database of the jth traction component. The thermal accumulation curve constructs a thermal capacity index function based on the thermal melting time constant of its traction motor, reactor and inverter, and judges the following items: If the growth rate of the heat accumulation curve per unit time If the first threshold Q1 of the set upper limit rate is exceeded, it is determined that the j-th traction component has a risk of thermal inertia mutation and a first-level warning instruction is generated; If the thermal balance coefficient RPH between the traction motor and the inverter is lower than the second thermal imbalance threshold Q2 for N consecutive time steps, it is determined that the cooling balance state of the j-th traction component is abnormal and a second-level warning instruction is generated; If the heat accumulation rate function If the corresponding temperature rise value at time t exceeds the third threshold value Q3 and lasts for a time interval greater than Δt, it is determined that the j-th traction component has a thermal critical overload risk and a third-level warning instruction is generated; If both: >Q1, RPH < thermal imbalance threshold Q2 for N consecutive time steps, If the corresponding temperature rise value at time t is greater than or equal to the third threshold value Q3 and the duration is greater than the time interval Δt, it is comprehensively judged that the j-th traction component has a precursor to thermal collapse and a high-level warning instruction is generated; The visual instruction module is used to generate a visual dynamic alarm map based on the warning instruction level of the j-th traction component, and to visually mark its operating status with thermal capacity consumption, including temperature rise trend, heat rate change, abnormal combination indication and residual heat release time estimation, to assist the train control system in status assessment and operation adjustment.

2. The data visualization management system based on the electromechanical industry according to claim 1 is characterized in that: The traction component modeling module includes a device identification unit and a parameter extraction unit: The device identification unit is used to identify and pair the jth traction component in the i-th train, where the traction component consists of a traction motor, a reactor, and an inverter. The unit collects information including the device's unique number, installation location, cooling method, rated operating level, and traction circuit number by reading device coding information from the train's traction control system, scanning the device's QR code or radio frequency tag, and retrieving device maintenance records, thereby establishing a traction component identification table. The parameter extraction unit is used to call the supporting equipment technical parameter documents and maintenance records according to the unique number of each device in the traction component identification table, extract the structural parameters, operating level parameters and thermal melting time constant of the traction motor, reactor and inverter, including: the rated power, rated speed, stator resistance, cooling type and thermal melting time constant of the traction motor; the rated current, equivalent inductance value, insulation level and thermal melting time constant of the reactor; the maximum bus voltage, switching frequency, IGBT module parameters and thermal melting time constant of the inverter; and form a comprehensive parameter set for the jth traction component.

3. The data visualization management system based on the electromechanical industry according to claim 2 is characterized in that: The traction component modeling module further includes a physical connection modeling unit: The physical connection modeling unit establishes a physical connection relationship diagram of the traction motor, reactor, and inverter based on the traction component identification table and equipment parameters, combined with the train traction system electrical wiring diagram and layout topology, and numbers and colors the connection relationships to form a three-dimensional functional model of the traction component; The specific steps of the 3D functional model of the traction components are as follows: based on the electrical wiring diagram and equipment installation layout diagram of the train traction system, the relative positions and connection relationships of the traction motor, reactor, and inverter in space are obtained to obtain the 2D layout data; The two-dimensional layout data is converted into spatial coordinates and input into the three-dimensional modeling software of Autodesk Inventor, SolidWorks or Siemens, and modeled in combination with the physical connection relationship diagram of the traction motor, reactor and inverter to form a three-dimensional functional model of the traction component.

4. The data visualization management system based on the electromechanical industry according to claim 3 is characterized in that: The working condition acquisition module includes a working condition sensing unit, a data extraction unit and a working condition database construction unit; The working condition sensing unit is used to collect the traction current value by deploying a current sensor at the traction motor input end and the inverter output side of the traction assembly of the i-th train; deploying a voltage sensor between the traction circuit DC bus and the AC output port to collect the traction voltage value; installing a torque sensor between the traction motor and the drive wheel system to collect the traction load torque; and installing a surface temperature sensor on the key hot surfaces of the traction motor, reactor and inverter housing to collect the surface temperature rise value of the equipment; The data extraction unit is used to extract time period data corresponding to acceleration, constant speed, climbing, braking, and regenerative braking conditions based on the raw data collected by the working condition sensing unit, using the synchronization technology of the GPS clock and the train event recording system, and to classify and extract the traction current, voltage, load torque, and equipment surface temperature rise index of the jth traction component according to the working condition type; The operating condition database construction unit is used to archive the extracted traction current, voltage, load torque and equipment surface temperature rise data according to five operating conditions: acceleration, constant speed, climbing, braking and regenerative braking, and establish a structured operating condition database with the jth traction component as the index unit.

5. The data visualization management system based on the electromechanical industry according to claim 4 is characterized in that: The thermal effect identification module includes a first calculation unit, a second calculation unit, a third calculation unit and an analysis unit; The first calculation unit is used to extract the traction current, voltage, load torque and equipment surface temperature rise of the j-th traction component under various working conditions from the working condition database, and obtain the thermal melt index function after dimensionless processing by combining the thermal melt time constant and structural parameters of the traction motor, reactor and inverter extracted from the comprehensive parameter set of the j-th traction component. .

6. The data visualization management system based on the electromechanical industry according to claim 5 is characterized in that: The second calculation unit is used to extract the equipment surface temperature rise data of the traction motor and inverter in the j-th traction component, and construct the thermal balance coefficient RPH after dimensionless processing.

7. The data visualization management system based on the electromechanical industry according to claim 5 is characterized in that: The third calculation unit is used to extract the traction data of each device in the jth traction assembly under various working conditions, including traction voltage value, traction load torque, traction equipment surface temperature rise and thermal melting time constant, and construct a heat accumulation rate function after dimensionless processing. .

8. The data visualization management system based on the electromechanical industry according to claim 5 is characterized in that: The analysis unit is used to convert the thermal melt index function Calculation is performed at each synchronous time point t to form a set of ordered heat accumulation points, which are plotted as heat accumulation curves in chronological order, and the growth rate is obtained. ; The first threshold Q1 is preset in advance, and the growth rate of the heat accumulation curve per unit time is Comparing and analyzing with the first threshold Q1 to obtain a first evaluation result includes: If the growth rate of the heat accumulation curve per unit time When the value is less than or equal to the first threshold Q1, it indicates that there is no risk of thermal inertia mutation for the jth traction component and continuous monitoring is required; If the growth rate of the heat accumulation curve per unit time When the value is greater than the first threshold Q1, it indicates that there is a risk of thermal inertia mutation in the jth traction component, and a first-level warning instruction is generated; The second threshold Q2 is preset in advance, and the thermal balance coefficient RPH between the traction motor and the inverter is compared and analyzed with the second threshold Q2 to obtain the second evaluation result, including: If the thermal balance coefficient RPH between the traction motor and the inverter is ≥ the thermal imbalance threshold Q2 in any of the N consecutive time steps, the cooling balance state of the traction component of the jth traction component is determined to be normal and is continuously monitored; If the thermal balance coefficient RPH between the traction motor and the inverter is less than the thermal imbalance threshold Q2 for N consecutive time steps, it is determined that the cooling balance state of the j-th traction component is abnormal, and a second-level warning instruction is generated; Extract the preset third threshold Q3 and transform the heat accumulation rate function Comparing and analyzing the corresponding temperature rise value at time t with the third threshold value Q3 to obtain the third evaluation result includes: If the heat accumulation rate function If the corresponding temperature rise value at time t is less than the third threshold value Q3, it is determined that the traction component does not have a thermal critical overload risk and is continuously monitored; If the heat accumulation rate function If the corresponding temperature rise value at time t is greater than or equal to the third threshold value Q3 and the duration is greater than the time interval Δt, it is determined that the traction component has a thermal critical overload risk and a third-level warning instruction is generated.

9. The data visualization management system based on the electromechanical industry according to claim 5 is characterized in that: The thermal effect identification module also includes a comprehensive analysis unit: The comprehensive analysis unit is used to meet the following conditions: the growth rate of the heat accumulation curve per unit time > first threshold Q1, thermal balance coefficient RPH between traction motor and inverter in N consecutive time steps < thermal imbalance threshold Q2, heat accumulation rate function If the corresponding temperature rise value at time t is greater than or equal to the third threshold value Q3 and the duration is greater than the time interval Δt, it is comprehensively judged that the j-th traction component has a precursor to thermal collapse, and the highest level warning instruction is generated.

10. The data visualization management system based on the electromechanical industry according to claim 9 is characterized in that: The visual instruction module includes a visual dynamic alarm map generation unit, a heat capacity consumption state standard unit and an auxiliary strategy unit; The visual dynamic warning map generation unit is used to generate a warning instruction level for the j-th traction component based on the thermal effect recognition module. Each warning level corresponds to an independent layer and is dynamically refreshed according to the time dimension, including: a heat accumulation curve trajectory, a heat balance coefficient fluctuation diagram, a temperature rise change curve, and a real-time slope vector of the heat rate slope; The heat capacity consumption state standard unit is used to visually mark the heat capacity consumption of the operating state of the j-th traction component, including: Temperature rise trend annotation: visualize the surface temperature rise trend of the traction motor, reactor and inverter on a graph, and mark the key temperature rise inflection points, temperature rise continuous sections and the color level corresponding to the current temperature rise level; Heat rate change annotation: Based on the change of the heat capacity exponential function over time, the growth rate mutation point and its corresponding time period are marked in the heat accumulation curve to form a slope change map to intuitively identify whether there is a stage-by-stage acceleration or abnormal sudden increase in the heat accumulation rate; Abnormal combination indication labeling: Abnormal combinations of thermal inertia mutation, cooling imbalance, thermal critical overload, and thermal collapse precursors are superimposed on the corresponding equipment layer in the form of graphical labels, forming a multi-level abnormal state joint indication to assist in locating the source and severity of the abnormality; Residual heat release time estimation: Based on the residual heat release time results provided by the evaluation module, the cooling time required is displayed in the form of a time scale below the graph. A color gradient bar indicates whether effective cooling can be completed before the next heavy load condition occurs, helping to determine whether the system can continue to operate under the current condition. The auxiliary strategy unit is used to generate operation adjustment suggestions according to the warning level, specifically including: Level 1 warning instructions prompt the cooling system to adjust, moderately reduce the load, reduce the operating power by 5% to 10%, and start the air cooling or liquid cooling system; The second-level warning command automatically starts the cooling system fault diagnosis module and reduces the traction pulse duty cycle to within 5%; Level 3 warning command: forced load reduction operation, execution of maximum thermal protection limit action, traction power reduction by 15%, forced activation of emergency cooling program, and limitation of continuous operation time; The highest level warning command activates interlock protection, stops inverter output, uploads fault instructions to the control center, and recommends emergency maintenance.

Images