A wind turbine blade transport vehicle anti-rollover warning method, system and storage medium

Abstract

The present application relates to the field of wind turbine blade transportation and discloses a wind turbine blade transport vehicle anti-rollover warning method, system, and storage medium, including the following steps: obtaining vehicle operating parameters; determining the vehicle driving state based on gyroscope parameters; storing the corresponding vehicle operating parameters in a preset parameter set, determining a state change model based on all vehicle operating parameters in the parameter set, and determining predicted operating parameters based on the state change model; generating a first warning coefficient based on the predicted operating parameters; determining whether the first warning coefficient exceeds a preset first threshold, and issuing an alarm if the first warning coefficient exceeds the first threshold. Based on the prediction of the vehicle operating parameters, the possibility of vehicle rollover can be detected in advance, and the operator can be reminded to stop improper operations in a timely manner.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine blade transportation, and in particular to an anti-rollover warning method, system and storage medium for a wind turbine blade transport vehicle. Background Art

[0002] With the country's vigorous development of clean energy, the development and utilization of clean energy is becoming more and more common. Among them, wind power generation has a rapid development momentum in my country, and the output of wind power generation equipment is very large.

[0003] Wind turbine blades typically measure 30 to 40 meters in length, with some reaching over 100 meters. Furthermore, given the distribution of wind resources in my country, wind farms are mostly located in plateaus and mountainous areas with complex terrain. Wind turbine blade transport equipment must perform multiple actions, including lifting, rotating, and pitching, to avoid obstacles. Therefore, specialized blade lifters are required to transport wind turbine blades over mountainous terrain.

[0004] The lifting, rotation, and pitch control operations of a blade lifter are performed while the vehicle is in motion. During this process, the vehicle lacks hydraulic outriggers to stabilize it, and the chassis is often not level. This can easily lead to rollovers when encountering curves or steep curves in mountainous terrain. Existing transport procedures rely entirely on operators observing road conditions and basing their operations on their experience. Inexperienced operators can easily misjudge road conditions, leading to operational errors and resulting in vehicle rollovers. Summary of the Invention

[0005] The present application discloses a wind turbine blade transport vehicle anti-rollover warning method, system and storage medium, which can monitor the transport status of the vehicle, predict the vehicle operation status in the short term in the future based on the changes in the collected vehicle transport status, and judge in advance whether continuing the current operation will cause the vehicle to roll over, thereby assisting the operator to complete the blade angle operation more safely and reducing the operator's requirements on operating experience.

[0006] In a first aspect, the present application provides a wind turbine blade transport vehicle anti-rollover warning method, which adopts the following technical solution:

[0007] A wind turbine blade transport vehicle anti-rollover warning method includes the following steps:

[0008] Acquiring vehicle operating parameters, wherein the vehicle operating parameters include gyroscope parameters, speed parameters, and blade parameters;

[0009] Determine the vehicle's driving state based on gyroscope parameters;

[0010] Determine whether the vehicle's driving status is consistent with the preset historical driving status.

[0011] If so, the corresponding vehicle operating parameters are stored in a preset parameter set, and a state change model is determined based on all vehicle operating parameters in the parameter set, wherein the parameter set stores vehicle operating parameters of the same historical driving state;

[0012] If not, update the historical driving state to the current vehicle driving state and clear the parameter set;

[0013] Determining predicted operating parameters based on the state change model, wherein the predicted operating parameters are vehicle operating parameters predicted after a preset time;

[0014] generating a first warning coefficient according to the predicted operating parameters;

[0015] Determine whether the first warning coefficient exceeds a preset first threshold,

[0016] If the first warning coefficient exceeds the first threshold, an alarm is issued.

[0017] Through the above technical solution, several vehicle operating parameters of the vehicle under the same driving state are collected, and the state change model of the current vehicle is determined based on this. The vehicle operating parameters of the vehicle in the next period of time are predicted based on the state change model, and a first warning coefficient is generated based on the predicted vehicle operating parameters. When the first warning coefficient exceeds a first threshold, an alarm is issued to remind the operator that continuing the current operation may cause the vehicle to overturn, so that the operator can discover and stop improper operations early, which can relatively reduce the requirements for the operator's operating experience.

[0018] Optionally, before updating the historical driving state to the current vehicle driving state and clearing the parameter set, the following steps are included:

[0019] Generate the second warning coefficient based on the current vehicle operating parameters,

[0020] Determine whether the second warning coefficient exceeds a preset second threshold, wherein the second threshold is lower than the first threshold,

[0021] If the second warning coefficient exceeds a preset second threshold, an alarm is issued.

[0022] Optionally, the state change model includes a vehicle change model and a blade change model; and determining the state change model according to all vehicle operating parameters in the parameter set includes the following steps:

[0023] determining a blade variation model based on all blade parameters in a parameter set;

[0024] A vehicle change model is determined based on all gyroscope parameters and corresponding speed parameters in a parameter set.

[0025] Optionally, determining the blade change model according to all blade parameters in the parameter set includes the following steps:

[0026] The blade parameters include blade angle;

[0027] Sort the blade angles according to the acquisition time to obtain the corresponding queue;

[0028] According to the changing trend of the blade angle in the queue, a corresponding basic model is matched from the preset basic models; the basic models include an increasing model, a decreasing model and a stable model;

[0029] Filter the blade angles in the queue that do not match the matched basic model.

[0030] Determine the model coefficient according to the proportional relationship between the difference in angles of adjacent blades in the queue and the time interval required to obtain the angles of adjacent blades;

[0031] The blade variation model is generated according to the matched basic model and model coefficients.

[0032] Optionally, matching a corresponding basic model from a preset basic model according to a change trend of the blade angle in the queue includes the following steps:

[0033] Calculate the difference in angles of adjacent blades in the queue one by one,

[0034] Classify the differences based on the magnitude of the values ​​to obtain a positive number set, a negative number set, and a positive and negative number set;

[0035] The basic model is determined according to the set containing the largest number of differences, where the positive set corresponds to the increasing model, the negative set corresponds to the decreasing model, and the set between positive and negative corresponds to the stable model.

[0036] Optionally, determining the vehicle change model according to all gyroscope parameters and corresponding speed parameters in the parameter set comprises the following steps:

[0037] Determine the vehicle moving section based on all gyroscope parameters and speed parameters in the parameter set;

[0038] Calculate the overlap between the vehicle moving section and several preset vehicle moving routes respectively.

[0039] A number of vehicle movement routes with high overlap are screened out, and corresponding vehicle change models are determined based on the screened vehicle movement routes.

[0040] Optionally, screening out a number of vehicle movement routes with high overlap comprises the following steps:

[0041] Determine whether the number of vehicle transport parameters corresponding to the current vehicle moving section exceeds the preset value,

[0042] If so, only the vehicle movement route with the highest overlap is used as the filtered vehicle movement route;

[0043] If not, the first N overlap degrees are selected in descending order of overlap degrees, and the corresponding vehicle movement routes are used as the screened vehicle movement routes, where N is a preset positive integer.

[0044] In a second aspect, the present application provides a wind turbine blade transport vehicle anti-rollover warning system, which adopts the following technical solutions:

[0045] A wind turbine blade transport vehicle anti-rollover warning system, comprising:

[0046] A data acquisition module, configured to acquire vehicle operating parameters, including gyroscope parameters, speed parameters, and blade parameters;

[0047] a data processing module that determines a vehicle driving state based on gyroscope parameters and determines whether the vehicle driving state is consistent with a preset historical driving state; if so, stores the corresponding vehicle operating parameters in a preset parameter set, and determines a state change model based on all vehicle operating parameters in the parameter set, wherein the parameter set stores vehicle operating parameters for the same historical driving state; if not, updates the historical driving state to the current vehicle driving state and clears the parameter set;

[0048] A prediction module, configured to determine a predicted operating parameter based on the state change model, wherein the predicted operating parameter is a vehicle operating parameter predicted after a preset time; and generate a first warning coefficient based on the predicted operating parameter;

[0049] The data judgment module is used to judge whether the first warning coefficient exceeds a preset first threshold value, and to issue an alarm if the first warning coefficient exceeds the first threshold value.

[0050] In a third aspect, the present application provides a readable storage medium storing a computer program that can be loaded by a processor and executed by the above-mentioned anti-rollover warning method for a wind turbine blade transport vehicle.

[0051] In summary, the present application includes at least one of the following beneficial technical effects: collecting several vehicle operating parameters of the vehicle under the same driving state, and determining the state change model of the current vehicle based on this, predicting the vehicle operating parameters of the vehicle in the next period of time based on the state change model, generating a first warning coefficient based on the predicted vehicle operating parameters, and issuing an alarm when the first warning coefficient exceeds a first threshold to remind the operator that continuing the current operation may cause the vehicle to overturn, thereby enabling the operator to discover and stop improper operations early, which can relatively reduce the requirements for the operator's operating experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flowchart of the overall steps of an embodiment of the present application.

[0053] Figure 2 It is a block diagram of the specific steps of determining the state change model in the embodiment.

[0054] Figure 3 It is a block diagram of the specific steps of determining the blade change model in the embodiment.

[0055] Figure 4 It is a block diagram of the specific steps of determining the vehicle change model in the embodiment. DETAILED DESCRIPTION

[0056] The present application is further described in detail below with reference to the accompanying drawings.

[0057] This application discloses a wind turbine blade transport vehicle anti-rollover warning method, see Figure 1 , including the following steps:

[0058] S100: Obtain vehicle operating parameters.

[0059] Vehicle operating parameters are obtained periodically, and the timing is set by the staff.

[0060] Vehicle operating parameters include gyroscope parameters, speed parameters, and blade parameters.

[0061] The gyroscope parameters are detected by a six-axis gyroscope installed on the wind turbine blade transport vehicle.

[0062] The speed parameter is obtained from the onboard system of the wind turbine blade transport vehicle.

[0063] Blade parameters include blade angle and blade weight. Blade weight is a fixed value set in advance by staff. Blade angle includes pitch angle and rotation angle. Blade angle is obtained from the control device installed on the wind turbine blade transporter that controls blade rotation and swing.

[0064] S200: Determine the vehicle driving state according to gyroscope parameters.

[0065] The vehicle driving state includes uphill turning, uphill straight driving, downhill turning, downhill straight driving, horizontal turning and horizontal straight driving. In one embodiment, turning includes left turning and right turning, that is, uphill turning includes uphill left turning and uphill right turning, downhill turning includes downhill left turning and downhill right turning, and horizontal turning includes horizontal left turning and horizontal right turning.

[0066] S300: Determine whether the vehicle driving state is consistent with a preset historical driving state.

[0067] The historical driving state is the vehicle state determined based on the gyroscope parameters obtained last time by the transport vehicle.

[0068] Judging whether the vehicle's driving state is consistent with the preset historical driving state is to verify whether the transport vehicle maintains the same motion state. When the transport vehicle maintains the same motion state, the vehicle operating parameters of the transport vehicle in this short period of time often have a certain connection, so the vehicle operating parameters in a short period of time can be estimated based on the vehicle operating parameters that have been obtained.

[0069] S400: If the vehicle driving state is consistent with a preset historical driving state, the corresponding vehicle operating parameters are stored in a preset parameter set, and a state change model is determined based on all vehicle operating parameters in the parameter set.

[0070] The parameter set stores vehicle operating parameters of the same historical driving state.

[0071] Vehicle movement is the change in direction and speed of the transporter in response to the driver's actions, such as steering, accelerating, or braking. Since drivers generally don't frequently switch between accelerating and braking, or between left and right turns, the vehicle will remain in a certain operating state for a period of time, and the parameter changes within this operating state are relatively stable. Therefore, the state change model can be determined by using the vehicle's operating parameters under the same historical driving state.

[0072] Of course, the blade transport vehicle will also experience changes in blade angle and orientation, in addition to the aforementioned changes in the vehicle itself. Therefore, building a vehicle stability model requires considering both vehicle and blade changes. Specifically, the state change model includes both a vehicle change model and a blade change model.

[0073] Furthermore, the state change model is determined based on all vehicle operating parameters in the parameter set, see Figure 2 , including the following steps:

[0074] S410 , determining a blade change model according to all blade parameters in a parameter set.

[0075] S420 : Determine a vehicle change model according to all gyroscope parameters and corresponding speed parameters in the parameter set.

[0076] The blade variation model is used to predict blade angles. The vehicle variation model is used to predict vehicle direction and speed. The blade variation model and vehicle variation model are linked by time. That is, at the same time point, the blade angle predicted by the blade variation model and the vehicle direction and speed predicted by the vehicle variation model together constitute the vehicle state at that time point.

[0077] S500: If the vehicle driving state is inconsistent with the preset historical driving state, the historical driving state is updated to the current vehicle driving state and the parameter set is cleared.

[0078] If the vehicle's driving state is inconsistent with the preset historical driving state, it means that the vehicle's current state has changed. The historical driving state previously stored in the parameter set can no longer accurately predict the subsequent vehicle operating parameters. Therefore, the parameter set is cleared. At the same time, the historical driving state is updated to ensure that the vehicle operating parameters under the same driving state are correctly stored in the parameter set.

[0079] S600: Determine predicted operating parameters according to the state change model.

[0080] The predicted operating parameters are vehicle operating parameters predicted after a preset time.

[0081] The preset time is set by the staff and is generally set to an integer multiple of the timing time for obtaining vehicle operating parameters. For example, if the timing time is 100ms, the preset time is 500ms.

[0082] S700: Generate a first warning coefficient according to the predicted operating parameters.

[0083] The first warning coefficient is used to indicate the possibility of the vehicle tipping over. The larger the first warning coefficient, the more likely the vehicle is to tip over. Specifically, the larger the speed parameter, the larger the vehicle steering angle, and the larger the blade angle, the larger the first warning coefficient.

[0084] S800: Determine whether the first warning coefficient exceeds a preset first threshold.

[0085] The first threshold is a critical value indicating that the vehicle may roll over.

[0086] S900: If the first warning coefficient exceeds a first threshold, an alarm is issued.

[0087] When the first warning coefficient exceeds the first threshold, it indicates that the vehicle is likely to roll over when operating according to the vehicle operating parameters corresponding to the first warning coefficient. Therefore, an alarm is issued to remind the operator to stop adjusting the blades, slow down the vehicle, or reduce the vehicle's rotation amplitude.

[0088] In one embodiment, the blade variation model is determined based on all blade parameters in the parameter set, see Figure 3 , including the following steps:

[0089] S411 , sorting the blade angles according to the order of acquisition time to obtain a corresponding queue.

[0090] The blade angle includes the pitch angle and the rotation angle. Therefore, sorting the blade angles actually means sorting the pitch angle and the rotation angle separately to facilitate subsequent data processing. However, the processing method for the two angles is the same. To simplify the content, the blade angle is used to represent the pitch angle and the rotation angle in the embodiment.

[0091] S412: Match a corresponding basic model from preset basic models according to the changing trend of the blade angles in the queue.

[0092] The basic models include the increasing model, the decreasing model and the stable model.

[0093] The basic model only expresses the relationship between the blade angle and time. For example, the increasing model expresses the relationship that the blade angle gradually increases with the increase of time, and the decreasing model expresses the relationship that the blade angle gradually decreases with the increase of time. As for the specific growth coefficient or decrease coefficient, they are still to be determined. The stable model expresses that the blade angle will not change with time, that is, the blade angle is a constant value, and the same constant value is not clear.

[0094] For a more intuitive approach, the basic model can be simplified into a formula:

[0095] The increasing model corresponds to Y=K*T, the decreasing model corresponds to Y=-K*T, and the stable model corresponds to Y=X.

[0096] Where Y is the blade angle, K is the model coefficient, T is time, and X is a constant value.

[0097] In one embodiment, matching a corresponding basic model from a preset basic model according to a change trend of blade angles in a queue includes the following steps:

[0098] S4121. Calculate the angle differences of adjacent blades in the queue in sequence.

[0099] S4122. Classify the differences based on the magnitude of the values ​​to obtain a positive number set, a negative number set, and a positive and negative number set.

[0100] S4123. Determine a basic model based on the set containing the largest number of differences.

[0101] Among them, the positive number set corresponds to the increasing model, the negative number set corresponds to the decreasing model, and the set between positive and negative corresponds to the stable model.

[0102] Because equipment detection allows for a certain degree of error, even if the blade remains unchanged, the measured blade angle may fluctuate slightly. This can result in data that clearly conforms to a stable model having non-zero differences. Therefore, the range corresponding to the positive and negative number set appropriately encompasses both sides of zero. For example, differences between -1 and 1 are all included in the positive and negative number set.

[0103] S413: Filter blade angles in the queue that do not conform to the matched basic model.

[0104] The filtering method is to judge whether the difference between adjacent blade angles belongs to the matched basic model in the order of acquisition time from the earliest to the later. If it does, the previous blade angle of the two blade angles corresponding to the current difference is retained; if it does not, the previous blade angle of the two blade angles corresponding to the current difference is deleted.

[0105] S414 , determining a model coefficient according to a proportional relationship between a difference in angles of adjacent blades in the queue and a time interval required to obtain the angles of adjacent blades.

[0106] A ratio can be calculated for each set of differences and the corresponding time interval. The average value is calculated based on all the ratios. This average value is the model coefficient. It should be noted that the model coefficient is an absolute value, so it needs to be converted to an absolute value after calculating the average value.

[0107] S415 : Generate a blade variation model according to the matched basic model and model coefficients.

[0108] Step S414 determines the model coefficients for both the increasing and decreasing models. Accordingly, once the model coefficients are determined, they are combined into a complete blade variation model through step S414. However, when converting from a stable model to a blade variation model, steps S414 and S415 are not necessary. Instead, the non-compliant blade angles are filtered out in step S413, and the average of the remaining blade angles is calculated. This average value becomes the constant value of the stable model.

[0109] In one embodiment, the vehicle change model is determined based on all gyroscope parameters and corresponding speed parameters in the parameter set, see Figure 4 , including the following steps:

[0110] S421. Determine a vehicle moving section based on all gyroscope parameters and speed parameters in the parameter set.

[0111] According to the gyroscope parameters, the corresponding speed parameters and the time interval for collecting vehicle operation parameters, a road section with a forward direction is generated. All road sections are connected in sequence according to the forward direction, and curve fitting is performed to generate a vehicle moving section.

[0112] S422: Calculate the overlap between the vehicle moving section and a plurality of preset vehicle moving routes respectively.

[0113] The overlap degree is the similarity obtained by comparing the current vehicle moving section with different sections in the vehicle moving route.

[0114] S423: Filter out several vehicle movement routes with high overlap, and determine corresponding vehicle change models based on the filtered vehicle movement routes.

[0115] Since vehicle movement doesn't strictly adhere to a single set of standards, i.e., the same vehicle and driver traveling the same road multiple times will likely have varying routes. Therefore, it's unlikely that there will be 100% overlap. Of course, the higher the overlap, the more likely the corresponding vehicle route is the current vehicle's route. Therefore, it's important to select routes with the highest overlap.

[0116] The selected vehicle movement routes can be directly used as vehicle change models. By selecting different time nodes, the vehicle operation parameters corresponding to the time nodes can be directly found from the vehicle movement routes.

[0117] In one embodiment, screening out a number of vehicle movement routes with high overlap includes the following steps:

[0118] S424: Determine whether the number of vehicle transportation parameters corresponding to the current vehicle movement section exceeds a preset value.

[0119] S425: If yes, only the vehicle movement route with the highest overlap is used as the selected vehicle movement route.

[0120] S426. If not, select the first N overlapping degrees in descending order, and use the corresponding vehicle movement routes as the selected vehicle movement routes, where N is a preset positive integer.

[0121] Theoretically, the preset vehicle movement routes are sufficiently comprehensive. Therefore, when the parameter set contains fewer vehicle operating parameters, the converted vehicle movement segments are relatively short. This means that multiple vehicle movement routes may share the same segment as the vehicle movement segment, making it easy to match multiple vehicle movement routes. However, due to the limited available data, it is difficult to further determine which vehicle movement route is more likely to be the route of the current vehicle. Therefore, only multiple vehicle movement routes with high overlap can be selected as the vehicle movement routes. If the first warning coefficient predicted based on any vehicle movement route subsequently exceeds the first threshold, an alarm will be issued.

[0122] When there are more vehicle operating parameters in the parameter set, the converted vehicle movement section will be relatively long, and the number of vehicle movement routes with high overlap will be greatly reduced. Therefore, the road corresponding to the vehicle movement route with the highest overlap is very likely to be the road on which the current vehicle is traveling. Relatively accurate vehicle operating parameters can be estimated based on this vehicle movement route alone.

[0123] In one embodiment, before updating the historical driving state to the current vehicle driving state and clearing the parameter set, the following steps are included:

[0124] S510: Generate a second warning coefficient according to current vehicle operating parameters.

[0125] S520: Determine whether the second warning coefficient exceeds a preset second threshold.

[0126] S530: If the second warning coefficient exceeds a preset second threshold, an alarm is issued.

[0127] The second warning coefficient is used to indicate the likelihood of the vehicle tipping over. A larger second warning coefficient indicates a higher likelihood of tipping over; conversely, a smaller second warning coefficient indicates a more stable vehicle. Specifically, the greater the speed parameter, the greater the vehicle's steering angle, or the larger the blade angle, the greater the second warning coefficient.

[0128] In terms of calculation method, the method for calculating the second warning coefficient is the same as the method for calculating the first warning coefficient, but the vehicle operating parameters on which the two are based are different in nature. The former uses the actual vehicle operating parameters, while the latter uses the predicted vehicle operating parameters.

[0129] Because only one vehicle operating parameter is collected during the current driving state, it cannot be used to predict subsequent vehicle operating parameters. Therefore, we can only assume that the subsequent vehicle operating parameters will become unstable. Therefore, it is necessary to determine whether the current vehicle operation is sufficiently stable. Only when the current vehicle operation is sufficiently stable can there be sufficient time to collect more data and issue early warnings. Therefore, the second threshold must be lower than the first threshold.

[0130] The purpose of judging whether the second warning coefficient exceeds the second threshold value is to judge whether the corresponding vehicle driving state is sufficiently stable.

[0131] The present application also discloses an anti-rollover warning system for a wind turbine blade transport vehicle, comprising:

[0132] The data acquisition module is used to acquire vehicle operating parameters, which include gyroscope parameters, speed parameters, and blade parameters.

[0133] The data processing module determines the vehicle driving state based on the gyroscope parameters and judges whether the vehicle driving state is consistent with the preset historical driving state. If so, the corresponding vehicle operating parameters are stored in a preset parameter set, and a state change model is determined based on all vehicle operating parameters in the parameter set, and the parameter set stores vehicle operating parameters of the same historical driving state; if not, the historical driving state is updated to the current vehicle driving state and the parameter set is cleared.

[0134] The prediction module is used to determine a predicted operating parameter based on the state change model, where the predicted operating parameter is a vehicle operating parameter predicted after a preset time; and generate a first warning coefficient based on the predicted operating parameter.

[0135] The data judgment module is used to judge whether the first warning coefficient exceeds a preset first threshold value, and to issue an alarm if the first warning coefficient exceeds the first threshold value.

[0136] An embodiment of the present application further discloses a readable storage medium storing a computer program that can be loaded by a processor and executed by the above-mentioned anti-rollover warning method for a wind turbine blade transport vehicle.

[0137] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A wind turbine blade transport vehicle anti-rollover warning method, characterized in that: The following steps are involved: Acquiring vehicle operating parameters, wherein the vehicle operating parameters include gyroscope parameters, speed parameters, and blade parameters; determining a vehicle driving state according to the gyroscope parameters; Determine whether the vehicle's driving state is consistent with a preset historical driving state, If so, the corresponding vehicle operating parameters are stored in a preset parameter set, and a state change model is determined based on all vehicle operating parameters in the parameter set, wherein the parameter set stores vehicle operating parameters of the same historical driving state, and the state change model includes a vehicle change model and a blade change model; if not, the historical driving state is updated to the current vehicle driving state and the parameter set is cleared; Determining a predicted operating parameter based on the state change model, wherein the predicted operating parameter is a vehicle operating parameter predicted after a preset time; generating a first warning coefficient according to the predicted operating parameters; Determine whether the first warning coefficient exceeds a preset first threshold, If the first warning coefficient exceeds the first threshold, an alarm is issued; Determining the state change model according to all vehicle operating parameters in the parameter set includes: determining the blade variation model according to all blade parameters in the parameter set, wherein the blade variation model is used to predict the blade angle; The vehicle change model is determined according to all gyroscope parameters and corresponding speed parameters in the parameter set, the vehicle change model is used to predict the vehicle direction and speed, and the blade change model and the vehicle change model are associated through time.

2. The anti-rollover warning method for a wind turbine blade transport vehicle according to claim 1, characterized in that: Before updating the historical driving state to the current vehicle driving state and clearing the parameter set, the following steps are included: Generate the second warning coefficient based on the current vehicle operating parameters, Determine whether the second warning coefficient exceeds a preset second threshold, wherein the second threshold is lower than the first threshold, If the second warning coefficient exceeds the preset second threshold, an alarm is issued.

3. The anti-rollover warning method for a wind turbine blade transport vehicle according to claim 1, characterized in that: Determining the blade change model according to all blade parameters in the parameter set includes the following steps: The blade parameters include blade angle; Sorting the blade angles according to the acquisition time to obtain a corresponding queue; Matching a corresponding basic model from a preset basic model according to the changing trend of the blade angle in the queue; the basic model includes an increasing model, a decreasing model and a stable model; Filter the blade angles in the queue that do not conform to the matched basic model, Determining a model coefficient according to a proportional relationship between a difference in angles of adjacent blades in the queue and a time interval required to obtain the angles of adjacent blades; The blade variation model is generated according to the matched basic model and the model coefficients.

4. The anti-rollover warning method for a wind turbine blade transport vehicle according to claim 3, characterized in that: The step of matching a corresponding basic model from a preset basic model according to the changing trend of the blade angles in the queue comprises the following steps: Calculate the difference between the angles of adjacent blades in the queue in sequence, Classifying the differences based on the magnitude of the values ​​to obtain a positive number set, a negative number set, and a positive and negative number set; The basic model is determined according to the set containing the largest number of the difference values, wherein the positive number set corresponds to the increasing model, the negative number set corresponds to the decreasing model, and the set between positive and negative corresponds to the stable model.

5. The anti-rollover warning method for a wind turbine blade transport vehicle according to claim 1, characterized in that: Determining the vehicle change model according to all gyroscope parameters and corresponding speed parameters in the parameter set comprises the following steps: determining a vehicle moving section based on all gyroscope parameters and speed parameters in the parameter set; Calculate the overlap between the vehicle moving section and several preset vehicle moving routes respectively, A number of vehicle movement routes with high overlap are screened out, and corresponding vehicle change models are determined based on the screened vehicle movement routes.

6. The anti-rollover warning method for a wind turbine blade transport vehicle according to claim 5, characterized in that: The method of selecting a plurality of vehicle movement routes with the highest overlap comprises the following steps: Determine whether the number of vehicle transport parameters corresponding to the current vehicle moving section exceeds the preset value, If so, only the vehicle movement route with the highest overlap is used as the filtered vehicle movement route; If not, the first N overlap degrees are selected in descending order according to the overlap degrees, and the corresponding vehicle movement routes are used as the screened vehicle movement routes, where N is a preset positive integer.

7. A wind turbine blade transport vehicle anti-rollover warning system, characterized in that: include: A data acquisition module, configured to acquire vehicle operating parameters, including gyroscope parameters, speed parameters, and blade parameters; a data processing module, configured to determine a vehicle driving state based on gyroscope parameters, and determine whether the vehicle driving state is consistent with a preset historical driving state; if so, store the corresponding vehicle operating parameters in a preset parameter set, and determine a state change model based on all vehicle operating parameters in the parameter set, wherein the parameter set stores vehicle operating parameters for the same historical driving state, and the state change model includes a vehicle change model and a blade change model; if not, update the historical driving state to the current vehicle driving state and clear the parameter set; a prediction module, configured to determine a predicted operating parameter based on the state change model, the predicted operating parameter being a vehicle operating parameter predicted after a preset time; and to generate a first warning coefficient based on the predicted operating parameter; a data judgment module, configured to judge whether the first warning coefficient exceeds a preset first threshold, and issue an alarm if the first warning coefficient exceeds the first threshold; The data processing module is further used to: determining the blade variation model according to all blade parameters in the parameter set, wherein the blade variation model is used to predict the blade angle; The vehicle change model is determined according to all gyroscope parameters and corresponding speed parameters in the parameter set, the vehicle change model is used to predict the vehicle direction and speed, and the blade change model and the vehicle change model are associated through time.

8. A readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes the anti-rollover warning method for a wind turbine blade transport vehicle according to any one of claims 1 to 6.

Images