Intelligent coal mine vehicle weighing data processing and optimizing algorithm and system

Abstract

The invention discloses an intelligent coal mine vehicle weighing data processing and optimization algorithm and system, relates to the technical field of data processing, and is used for solving the problems of abnormal measurement and the like caused by a vehicle following phenomenon when a coal mine vehicle is weighed, and the method comprises the steps: calculating the loading and unloading timestamps of a weighed vehicle sample through obtaining the internal and external momentums of the vehicle sample; the vehicle samples are weighed through the calculated timestamps, the vehicle sample states are determined according to the vehicle sample weighing detected by the different timestamps, and the vehicle sample weighing accuracy can be improved through the calculated loading and unloading timestamps. The speed of front and rear vehicle samples entering a weighing area and the time difference of loading and unloading are collected, the vehicle following phenomenon risk is analyzed by using a KNN algorithm, an instruction is made according to the calculated timestamp and the vehicle following phenomenon risk analysis result, and corresponding response is made according to the instruction, so that the vehicle weighing data abnormity caused by the vehicle following phenomenon is reduced. And the safety guarantee of the coal mine data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and more specifically, to an intelligent coal mine vehicle weighing data processing and optimization algorithm and system. Background Art

[0002] Data processing technology refers to methods and technologies used to collect, organize, analyze and interpret data. When data processing technology is applied to coal mine vehicle weighing data processing, the weight data of coal mines and coal transport vehicles can be obtained more accurately and conveniently.

[0003] The prior art has the following deficiencies:

[0004] In the past, when coal mining vehicles were weighed, due to the large amount of coal, in order to improve coal transportation efficiency, the coal mining vehicles followed the vehicle closely and at a similar speed when weighing, which made it easy for the vehicle to follow the vehicle, resulting in large deviations in detection data and low data accuracy when the coal mining vehicles were weighed. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent coal mine vehicle weighing data processing and optimization algorithm and system, which determines the detection abnormality of vehicle samples by analyzing the detection timestamps and following vehicle phenomena of vehicle samples and performs response processing to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent coal mine vehicle weighing data processing and optimization system, comprising a data acquisition module, a data analysis module and a response processing module;

[0008] The data acquisition module determines the vehicle sample's internal and external momentum, the speed at which the front and rear vehicle samples enter the weighing area, and the time difference between weighing and weighing by accessing the automatic identification system, and transmits it to the data analysis module;

[0009] The data analysis module receives the in-vehicle and out-vehicle momentum of the vehicle sample and calculates the weighing timestamp of the vehicle sample on and off the scale, weighs the vehicle sample at each weighing timestamp, and sets the first instruction according to the weighing result, receives the speed of the front and rear vehicle samples entering the weighing area and the time difference of on and off the scale, uses the KNN algorithm to analyze the vehicle following phenomenon, and sets the second instruction according to the analysis result, and transmits the set first instruction and second instruction to the response processing module;

[0010] The response processing module is used to receive the instructions transmitted by the data analysis module, determine the weighing value of the vehicle sample according to the first instruction, and review and adjust the weighing value of the vehicle sample according to the second instruction.

[0011] In a preferred embodiment, the automatic identification system is a system that automatically identifies, tracks and manages objects, and is used to determine the location and volume of vehicle samples and the coal mines in the vehicle samples, thereby obtaining the volume of the vehicle samples, the volume of the coal mines in the vehicle, the displacement of the vehicle samples, and the displacement and direction of the coal mines in the vehicle.

[0012] In a preferred embodiment, when determining the in-vehicle and out-vehicle momentum of a vehicle sample, the data acquisition module takes the cosine value of the displacement of the coal mine in the vehicle in the displacement direction to obtain the displacement of the coal mine in the horizontal direction based on the vehicle sample and the displacement amount and displacement direction of the coal mine in the vehicle, multiplies the volume of the displaced coal mine in the vehicle by the horizontal displacement amount as the in-vehicle momentum, and multiplies the volume of the vehicle sample by the displacement amount as the out-vehicle momentum.

[0013] In a preferred embodiment, the data analysis module performs vector summation of the momentum inside the vehicle and the momentum outside the vehicle, and if the result is 0, the corresponding time point is used as the weighing timestamp.

[0014] In a preferred embodiment, the data analysis module sets a period of time as analysis time before receiving the speed of the front and rear vehicle samples entering the weighing area and the time difference of weighing and weighing. During the analysis time, the speed of multiple vehicle samples entering the weighing area and the time difference of weighing and weighing are obtained, and the KNN algorithm is used to analyze the vehicle following phenomenon.

[0015] In a preferred embodiment, the KNN algorithm is a similarity classification method, which uses similarity to classify the prediction results, and can be used to analyze the risk level of the car-following phenomenon of adjacent vehicle samples. The data analysis module uses the KNN algorithm to analyze the car-following phenomenon. The specific steps are as follows:

[0016] Calculate the vehicle following influence coefficient: calculate the speed difference of adjacent vehicle samples entering the weighing area during the analysis time, randomly select the speed difference and the time difference of weighing and weighing of adjacent vehicle samples as a feature combination, and calculate the vehicle following influence coefficient of the feature combination according to the actual impact of the vehicle following phenomenon;

[0017] Perform similarity screening: Perform similarity screening on each vehicle-following influence coefficient calculated by the feature combination, set a similarity threshold using the vehicle-following influence coefficient, and perform similarity classification on each feature combination according to the similarity threshold;

[0018] Analyze the risk of car following: When the car following influence coefficient calculated by adjacent vehicle samples exceeds the similarity threshold, it is classified as a low-risk feature combination and the risk of car following is judged to be low; otherwise, the risk of car following is judged to be high.

[0019] In a preferred embodiment, the actual impact of the car-following phenomenon is that the smaller the speed difference or the time difference between the upper and lower scales of adjacent vehicle samples is, the greater the car-following impact coefficient is. The speed difference or the time difference between the upper and lower scales of adjacent vehicle samples is normalized, and then the sum is taken to obtain the car-following impact coefficient;

[0020] The similarity threshold is set by the percentile method, the vehicle following influence coefficients are arranged from small to large, N% is set as the similarity ratio, and the vehicle following influence coefficients exceeding N% of the data are used as the similarity threshold.

[0021] In a preferred embodiment, the data analysis module will formulate a first instruction once each time it obtains a weighing timestamp, and will formulate a second instruction once each time it calculates the vehicle-following risk coefficient for two adjacent vehicle samples and determines the risk of the vehicle-following phenomenon. The data analysis module transmits the first instruction and the second instruction to the response processing module.

[0022] An intelligent coal mine vehicle weighing data processing and optimization algorithm is used to implement the above-mentioned intelligent coal mine vehicle weighing data processing and optimization system, including the following responses:

[0023] After receiving the first instruction, the response processing module weighs the vehicle sample once. When the vehicle sample passes the preset number of tests and ends weighing, the response processing module will count the number of occurrences of 0. If the number of 0 is the same as the number of tests, it will display a weighing abnormality. The response processing module compares whether the results of weighing the vehicle sample each time the first instruction is received are the same. If they are the same, the cumulative number of the same results is recorded. After the vehicle sample is finished weighing, the weighing result with the largest cumulative number of times is used as the weighing value of the vehicle sample.

[0024] After receiving the second instruction, the response processing module takes the weighing result with the largest cumulative number of times as the weighing value of the previous vehicle sample if the adjacent vehicle sample is judged to have a low risk of vehicle following; if the adjacent vehicle sample is judged to have a high risk of vehicle following, the maximum number of weighing times during the weighing time of the previous vehicle sample is taken as the stable weighing value of the previous vehicle sample, and compared with the preset stability threshold; if the stable weighing value is less than the stability threshold, a weighing abnormality is displayed; otherwise, the stable weighing value of the previous vehicle sample is taken as the weighing value of the previous vehicle sample.

[0025] The technical effects and advantages of an intelligent coal mine vehicle weighing data processing and optimization algorithm and system of the present invention are as follows:

[0026] The present invention obtains the in-vehicle and out-vehicle momentum of the vehicle sample to calculate the timestamps of weighing and weighing the vehicle sample, weighs the vehicle sample by calculating the obtained timestamps, and determines the vehicle sample status according to the weighing of the vehicle samples detected by different timestamps. The accuracy of weighing the vehicle sample can be improved by calculating the timestamps of weighing and weighing obtained, and the speed of the vehicle samples entering the weighing area before and after the collection and the time difference of weighing and weighing are used to analyze the risk of the following vehicle phenomenon. Instructions are formulated by combining the calculated timestamps and the results of the risk analysis of the following vehicle phenomenon, and corresponding responses are made according to the instructions, thereby reducing the abnormal vehicle weighing data caused by the following vehicle phenomenon, and improving the security of coal mine data. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a schematic diagram of an intelligent coal mine vehicle weighing data processing and optimization system of the present invention.

[0028] Figure 2 This is a flow chart of an intelligent coal mine vehicle weighing data processing and optimization system of the present invention.

[0029] Figure 3 This is a response diagram of an intelligent coal mine vehicle weighing data processing and optimization algorithm of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0031] The present invention obtains the in-vehicle and out-vehicle momentum of the vehicle sample to calculate the timestamps of weighing and weighing the vehicle sample, weighs the vehicle sample by calculating the obtained timestamps, determines the vehicle sample status according to the weighing of the vehicle samples detected by different timestamps, collects the speeds of the vehicle samples entering the weighing area before and after, and the time difference of weighing and weighing to analyze the risk of the following vehicle phenomenon, formulates instructions by combining the calculated timestamps and the results of the risk analysis of the following vehicle phenomenon, and makes corresponding responses according to the instructions, thereby reducing the abnormal vehicle weighing data caused by the following vehicle phenomenon.

[0032] Embodiment, an intelligent coal mine vehicle weighing data processing and optimization algorithm and system, such as Figure 1 As shown, it includes a data acquisition module, a data analysis module and a response processing module;

[0033] The data acquisition module determines the vehicle sample's internal and external momentum, the speed at which the front and rear vehicle samples enter the weighing area, and the time difference between weighing and weighing by accessing the automatic identification system, and transmits it to the data analysis module;

[0034] The data analysis module receives the in-vehicle and out-vehicle momentum of the vehicle sample and calculates the weighing timestamp of the vehicle sample on and off the scale, weighs the vehicle sample at each weighing timestamp, and sets the first instruction according to the weighing result, receives the speed of the front and rear vehicle samples entering the weighing area and the time difference of on and off the scale, uses the KNN algorithm to analyze the vehicle following phenomenon, and sets the second instruction according to the analysis result, and transmits the set first instruction and second instruction to the response processing module;

[0035] The response processing module is used to receive the instructions transmitted by the data analysis module, determine the weighing value of the vehicle sample according to the first instruction, and review and adjust the weighing value of the vehicle sample according to the second instruction.

[0036] The functions of each module are as follows:

[0037] The data acquisition module determines the internal and external momentum of the vehicle sample by accessing the automatic identification system. The internal and external momentum are generated by the displacement of the coal mine in the vehicle sample and the vehicle itself respectively. The external momentum is the displacement of the vehicle sample caused by various reasons during weighing, and the internal momentum is the displacement of the coal mine from its original position when the vehicle sample is weighed. It should be explained that since some of the loaded items on the vehicle are prone to displacement after weighing and unweighing, for example, after the coal mine is loaded, the top coal mine migrates to the bottom, which will cause unstable vehicle detection or large deviations in detection results.

[0038] When detecting the speed of the front and rear vehicle samples entering the weighing area, a speed sensor can be installed in front of the weighing area. Whenever a vehicle passes by, the speed sensor will record the passing speed of the vehicle sample. The time difference between weighing and unweighing is calculated by setting a trigger point on the weighing instrument and recording the time after the trigger point is triggered. The trigger point can be set to record a time point each time the reading on the weighing platform returns to zero. Each time the first non-zero data appears, a time point is recorded. The time difference between weighing and unweighing can be obtained by subtracting the later recorded time point from the previous recorded time point. For example, after the weighing of the previous vehicle sample is completed, the reading on the weighing instrument returns to zero and the time point is recorded. When the next vehicle sample is weighed, the reading on the weighing instrument begins to change. When the reading on the weighing instrument changes, the time point is immediately recorded. The time difference between weighing and unweighing between the two vehicles is obtained by subtracting the two time points.

[0039] It should be noted that the automatic identification system is a system for automatically identifying, tracking and managing objects. It can determine the location of vehicle samples and coal mines within the vehicle samples, thereby determining the momentum of the vehicle samples inside and outside the vehicle. The speed sensor is a device that measures the speed of an object and can be used to record the speed of the vehicle sample.

[0040] When receiving the internal and external momentum of the vehicle sample, the data analysis module obtains the displacement amount and displacement direction of the vehicle sample and the coal mine, and calculates the weighing timestamp of the vehicle sample on and off the scale. The specific steps are as follows:

[0041] Determine the volume of the vehicle sample and the volume of the coal mine in the vehicle. According to the displacement and displacement direction of the vehicle sample and the coal mine in the vehicle, since the displacement of the vehicle sample can only be horizontal displacement, for the coal mine in the vehicle, take the cosine value of the displacement of the coal mine in the vehicle in the displacement direction to obtain the displacement of the coal mine in the horizontal direction. Use the automatic identification system to obtain the volume of the coal mine that has been displaced in the vehicle and the volume of the vehicle sample. Multiply the volume of the coal mine that has been displaced in the vehicle by the horizontal displacement as the momentum inside the vehicle, and multiply the volume of the vehicle sample by the displacement as the momentum outside the vehicle. The momentum is vector summed. If the result is 0, the corresponding time point is used as the weighing timestamp. It should be explained that the vector summation distinguishes the direction on the basis of the summation. When the directions of the two summed values ​​are the same, they are added. When the summed values ​​in the two directions are opposite, they are subtracted. When determining the weighing timestamp, since the calculation result is set to 0, there is no need to set one of the two directions in the horizontal direction as the main direction. The weighing timestamp is the time point for weighing the truck. By setting multiple weighing timestamps to weigh the truck, a more accurate data basis can be provided for analyzing the weighing data of vehicle samples.

[0042] The data analysis module sets a period of time as the analysis time before receiving the speed of the front and rear vehicle samples entering the weighing area and the time difference of weighing and weighing. During the analysis time, the speed of multiple vehicle samples entering the weighing area and the time difference of weighing and weighing are obtained, and the KNN algorithm is used to analyze the vehicle following phenomenon. The specific steps are as follows:

[0043] The speed difference of adjacent vehicle samples entering the weighing area is calculated, and the calculated speed difference is merged into a speed difference data set, and the time difference of weighing and weighing of adjacent vehicle samples is merged into a time difference data set. The data of the speed difference data set and the data of the time difference data set are randomly selected and merged as a feature combination, that is, each feature combination contains the speed difference and the time difference of weighing and weighing of adjacent vehicle samples. The data in the feature combination are normalized, and the normalized results are marked as a and b respectively. The following vehicle influence coefficient of the feature combination is calculated according to the actual influence of the following vehicle phenomenon. The calculation formula of the following vehicle influence coefficient can be: G=-(a+b), wherein G is the following vehicle influence coefficient, and a and b are the normalized results of the speed difference and time difference in the feature combination respectively.

[0044] It needs to be explained that there is no unique method for normalizing data in the feature combination. The car-following phenomenon is that on the weighing platform, due to the large distance between the rear car and the front car, the two cars are weighed at the same time. However, after weighing, both become the weighing data of the front car, and the weighing quantity will be reduced and the data will be disordered. When the driving speed of the front and rear cars entering the weighing area is not much different or the distance between the front car unweighing time and the rear car weighing time is large, it is more likely to cause the car-following phenomenon. Therefore, the smaller the speed difference between adjacent vehicle samples or the time difference between adjacent vehicle samples getting on and off the scale is, the larger the car-following influence coefficient is, and the more likely the car-following phenomenon is to occur.

[0045] Perform similarity screening on each vehicle following influence coefficient calculated by the feature combination, use the vehicle following influence coefficient to set a similarity threshold, classify each feature combination similarly according to the similarity threshold, use the percentile method to set the similarity threshold, arrange the vehicle following influence coefficients from small to large, set N% as the similarity ratio, set a similarity threshold for the vehicle following influence coefficient according to the similarity ratio, and use the vehicle following influence coefficients that exceed N% of the data in the vehicle following influence coefficients as the similarity threshold. For example, set the similarity ratio to 30%, and use the vehicle following influence coefficients that exceed 30% of the vehicle following influence coefficients as the similarity threshold.

[0046] When the following vehicle impact coefficient exceeds the similarity threshold, its feature combination is marked as a low-risk feature combination; when the following vehicle impact coefficient is lower than the similarity threshold, its feature combination is marked as a high-risk feature combination. When the following vehicle phenomenon of adjacent vehicles is subsequently analyzed, the speed at which the adjacent vehicle samples enter the weighing area and the time difference between weighing and weighing are collected and the following vehicle impact coefficient is calculated. It is determined to which marked feature combination the following vehicle impact coefficient calculated by the adjacent vehicle samples belongs. When the following vehicle impact coefficient calculated by the adjacent vehicle samples exceeds the similarity threshold, it is classified as a low-risk feature combination, and the risk of the following vehicle phenomenon is judged to be low; when the following vehicle impact coefficient calculated by the adjacent vehicle samples is lower than the similarity threshold, it is classified as a high-risk feature combination, and the risk of the following vehicle phenomenon is judged to be high.

[0047] The data analysis module will formulate a first instruction every time it obtains a weighing timestamp, and will formulate a second instruction every time it calculates the vehicle-following risk coefficient of two adjacent vehicle samples and determines the risk of vehicle-following phenomenon. The data analysis module transmits the first instruction and the second instruction to the response processing module.

[0048] It should be noted that the calculation of the vehicle-following influence coefficient and the setting of the similarity threshold can be set by oneself as long as it conforms to the actual situation. The KNN algorithm is a similarity classification method, which uses similarity to classify the prediction results and can be used to analyze the risk level of the vehicle-following phenomenon of adjacent vehicle samples.

[0049] After receiving the first instruction, the response processing module weighs the vehicle sample once, and dynamically plans the weighing time according to the preset number of detections. For example, if the number of detections is set to 4, the response processing module ends weighing the vehicle sample after receiving four first instructions. After detecting the weighing value of the vehicle sample, the response processing module compares it with the preset zero limit value. If the weighing value is less than the zero limit value, the detection is set to 0; if the weighing value exceeds the zero limit value, a count is performed; if the weighing value of the vehicle sample exceeds the zero limit value within the number of detections, the count is canceled.

[0050] When the vehicle sample has passed the preset number of tests and finished weighing, the response processing module will count the number of occurrences of 0. If the number of 0 is the same as the number of tests, a weighing abnormality will be displayed. For example, when the number of tests is 3, when the number of occurrences of 0 is 3, a weighing abnormality will be displayed. If the vehicle sample weighing value is not 0 in the number of tests, a secondary test will be performed on the data stability of the vehicle sample.

[0051] When the response processing module performs a secondary test on the data stability of the vehicle sample, it compares whether the results of weighing the vehicle sample each time the first instruction is received are the same. If they are the same, the cumulative number of identical results is recorded. When the vehicle sample is finished weighing, the weighing result with the largest cumulative number of times is used as the weighing value of the vehicle sample.

[0052] After receiving the second instruction, the response processing module takes the weighing result with the largest cumulative number of times as the weighing value of the previous vehicle sample if the adjacent vehicle sample is judged to have a low risk of following the vehicle; if the adjacent vehicle sample is judged to have a high risk of following the vehicle, special processing of "non-stop weighing" is performed. The response processing module selects the maximum number of weighing times during the weighing time of the previous vehicle sample as the stable weighing value of the previous vehicle sample, and compares it with the preset stability threshold. If the stable weighing value is less than the stability threshold, the previous vehicle sample is judged to have been weighed without stopping, and a weighing abnormality is displayed; if the stable weighing value exceeds the stability threshold, the previous vehicle sample is judged to have not undergone non-stop weighing, and the stable weighing value of the previous vehicle sample is taken as the weighing value of the previous vehicle sample.

[0053] It should be noted that the number of tests and the zero limit mentioned above can be set according to actual conditions. The change of the number of tests can control the accuracy of vehicle sample weighing. The setting of the zero limit can avoid a large degree of detection errors. When weighing vehicle samples, obvious data errors can be eliminated by the zero limit. For example, the number of tests is set to 10 times and the zero limit is set to 50kg. When weighing vehicle samples, if weight data below 50kg appears, it is directly set to 0. The stability threshold is set by professionals in this field and will not be elaborated here.

[0054] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0055] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0056] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0057] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0058] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent coal mine vehicle weighing data processing and optimization system, characterized in that: It includes data acquisition module, data analysis module and response processing module; The data acquisition module determines the vehicle sample's internal and external momentum, the speed of the front and rear vehicle samples entering the weighing area, and the time difference between weighing and weighing by accessing the automatic identification system, and transmits it to the data analysis module; The data analysis module receives the in-vehicle and out-vehicle momentum of the vehicle sample and calculates the weighing timestamp of the vehicle sample on and off the scale, weighs the vehicle sample at each weighing timestamp, and sets the first instruction according to the weighing result, receives the speed of the front and rear vehicle samples entering the weighing area and the time difference of on and off the scale, uses the KNN algorithm to analyze the vehicle following phenomenon, and sets the second instruction according to the analysis result, and transmits the set first instruction and second instruction to the response processing module; The response processing module is used to receive the instructions transmitted by the data analysis module, determine the weighing value of the vehicle sample according to the first instruction, and review and adjust the weighing value of the vehicle sample according to the second instruction.

2. The intelligent coal mine vehicle weighing data processing and optimization system according to claim 1 is characterized in that: The automatic identification system is a system that automatically identifies, tracks and manages objects. It is used to determine the location and volume of vehicle samples and the coal mines in the vehicle samples, thereby obtaining the volume of the vehicle samples, the volume of the coal mines in the vehicle, the displacement of the vehicle samples, and the displacement and direction of the coal mines in the vehicle.

3. The intelligent coal mine vehicle weighing data processing and optimization system according to claim 2 is characterized in that: When determining the in-vehicle and out-vehicle momentum of the vehicle sample, the data acquisition module takes the cosine value of the displacement of the coal mine in the vehicle in the displacement direction to obtain the horizontal displacement of the coal mine in the vehicle based on the vehicle sample and the displacement amount and displacement direction of the coal mine in the vehicle. The volume of the displaced coal mine in the vehicle is multiplied by the horizontal displacement as the in-vehicle momentum, and the volume of the vehicle sample is multiplied by the displacement as the out-vehicle momentum.

4. The intelligent coal mine vehicle weighing data processing and optimization system according to claim 1 is characterized in that: The data analysis module performs vector summation of the momentum inside the vehicle and the momentum outside the vehicle. If the result is 0, the corresponding time point is used as the weighing timestamp.

5. The intelligent coal mine vehicle weighing data processing and optimization system according to claim 1 is characterized in that: Before receiving the speed of the front and rear vehicle samples entering the weighing area and the time difference of getting on and off the scale, the data analysis module sets a period of time as the analysis time. During the analysis time, the speed of multiple vehicle samples entering the weighing area and the time difference of getting on and off the scale are obtained, and the KNN algorithm is used to analyze the vehicle following phenomenon.

6. The intelligent coal mine vehicle weighing data processing and optimization system according to claim 5 is characterized by: The KNN algorithm is a similarity classification method that uses similarity to classify prediction results. It can be used to analyze the risk level of the following vehicle phenomenon of adjacent vehicle samples. The data analysis module uses the KNN algorithm to analyze the following vehicle phenomenon. The specific steps are as follows: Calculate the vehicle following influence coefficient: calculate the speed difference of adjacent vehicle samples entering the weighing area during the analysis time, randomly select the speed difference and the time difference of weighing and weighing of adjacent vehicle samples as a feature combination, and calculate the vehicle following influence coefficient of the feature combination according to the actual impact of the vehicle following phenomenon; Perform similarity screening: Perform similarity screening on each vehicle-following influence coefficient calculated by the feature combination, set a similarity threshold using the vehicle-following influence coefficient, and perform similarity classification on each feature combination according to the similarity threshold; Analyze the risk of following a vehicle: When the following influence coefficient calculated by the adjacent vehicle samples exceeds the similarity threshold, it is classified as a low-risk feature combination and the risk of following a vehicle is judged to be low; Otherwise, it is judged that the risk of following a vehicle is high.

7. The intelligent coal mine vehicle weighing data processing and optimization system according to claim 6 is characterized by: The actual impact of the car-following phenomenon is that the smaller the speed difference or the time difference between the adjacent vehicle samples, the greater the car-following impact coefficient. The speed difference or the time difference between the adjacent vehicle samples is normalized, and then the sum is taken to obtain the inverse number to obtain the car-following impact coefficient. The similarity threshold is set by the percentile method, the vehicle following influence coefficients are arranged from small to large, N% is set as the similarity ratio, and the vehicle following influence coefficients exceeding N% of the data are used as the similarity threshold.

8. An intelligent coal mine vehicle weighing data processing and optimization system according to any one of claims 4 or 6, characterized in that: The data analysis module will formulate a first instruction every time it obtains a weighing timestamp, and will formulate a second instruction every time it calculates the vehicle-following risk coefficient of two adjacent vehicle samples and determines the risk of vehicle-following phenomenon. The data analysis module transmits the first instruction and the second instruction to the response processing module.

9. An intelligent coal mine vehicle weighing data processing and optimization algorithm, based on an intelligent coal mine vehicle weighing data processing and optimization system according to any one of claims 1 to 8, characterized in that: The responses include: After receiving the first instruction, the response processing module weighs the vehicle sample once. When the vehicle sample passes the preset number of tests and ends weighing, the response processing module will count the number of occurrences of 0. If the number of 0 is the same as the number of tests, it will display a weighing abnormality. The response processing module compares whether the results of weighing the vehicle sample each time the first instruction is received are the same. If they are the same, the cumulative number of the same results is recorded. After the vehicle sample is finished weighing, the weighing result with the largest cumulative number of times is used as the weighing value of the vehicle sample. After receiving the second instruction, the response processing module takes the weighing result with the largest cumulative number of times as the weighing value of the previous vehicle sample if the adjacent vehicle sample is judged to have a low risk of vehicle following; if the adjacent vehicle sample is judged to have a high risk of vehicle following, the maximum number of weighing times during the weighing time of the previous vehicle sample is taken as the stable weighing value of the previous vehicle sample, and compared with the preset stability threshold; if the stable weighing value is less than the stability threshold, a weighing abnormality is displayed; otherwise, the stable weighing value of the previous vehicle sample is taken as the weighing value of the previous vehicle sample.

Images