A method for monitoring automated equipment for tree transplanting of garden excavating machinery

Abstract

The present invention relates to the technical field of planting machinery, and specifically to a method for monitoring automated tree transplanting equipment of a garden excavator, which obtains the pressure data sequence and resistance data sequence corresponding to each operation cycle of a plurality of soil cutting arms of the garden excavator to be monitored in the current period, and determines the single operation abnormality factor and the continuous operation abnormality factor based on the pressure data sequence and the resistance data sequence; determines the comprehensive fault degree of the garden excavator to be monitored by combining the single operation abnormality factor and the continuous operation abnormality factor of each soil cutting arm; and monitors the state of the garden excavator based on the comprehensive fault degree. The present invention obtains the mechanical state monitoring result by determining the comprehensive fault degree, and then adjusts the mechanical operation to plant trees based on the monitoring result, so that the survival rate of tree planting can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of planting machinery, and in particular to a monitoring method for automated tree transplanting equipment of a garden digging machinery. Background Art

[0002] In the garden tree planting project, the soil cutting arm of the garden excavator (planting machine) is not only used to dig the soil for the planting of trees, but also involves the fine treatment of the tree root system to ensure the minimum damage to the trees during the planting process and the survival rate after planting. Therefore, in order to improve the planting efficiency and the survival rate of the trees, it is necessary to monitor the operation status of the soil cutting arm in real time to avoid unexpected failures that will result in a low survival rate after the trees are planted.

[0003] In the traditional fault detection process of cutting arm operation, there are still factors that affect the accuracy of fault detection, such as analytical limitations, strong dependence on data quality, and neglect of environmental impact. For example, the failure mode of equipment may be different in different environments. Specifically, in a harsh environment, the equipment may show early wear or abnormality, but the abnormality shown at this time is not the actual abnormality of the equipment, while in a more ideal environment, the equipment may run for a long time without fault. If the fault detection system fails to take environmental factors into account, two problems may occur: one is to miss the real fault that appears in a specific environment, and the other is to misjudge the impact of environmental factors as a fault, resulting in inaccurate monitoring results. This inaccurate monitoring may cause errors in the operation of garden excavators. Summary of the invention

[0004] In order to solve the technical problem of poor accuracy in monitoring the operation fault of the soil cutting arm, the present invention aims to provide a monitoring method for automated tree transplanting equipment of a garden excavator. The technical solution adopted is as follows: An embodiment of the present invention provides a method for monitoring automated tree transplanting equipment of a garden excavator, the method comprising the following steps: S1, obtaining the pressure data sequence and resistance data sequence corresponding to each operation cycle of several cutting arms of the garden excavator to be monitored in the current period; S2, determining a single operation abnormality factor of each soil cutting arm according to the pressure data sequence and resistance data sequence corresponding to each soil cutting arm in the same operation cycle; S3, determining the continuous operation abnormality factor of each soil cutting arm according to the pressure data sequence corresponding to different operation cycles of the same soil cutting arm; S4, combining the single operation abnormality factor of each soil cutting arm and the continuous operation abnormality factor to determine the comprehensive fault degree of the garden excavator to be monitored; S5, monitor the condition of garden excavation machinery based on the comprehensive fault degree.

[0005] Furthermore, the determination step of S2 includes: Taking any soil cutting arm as the target soil cutting arm, analyzing the difference in the change trend between pressure and resistance according to the pressure data sequence and resistance data sequence corresponding to any operation cycle of the target soil cutting arm, and determining the first abnormal index of the target soil cutting arm in the operation cycle; Determine each pressure growth rate of the target cutting arm during the operation cycle from the beginning to full load, and screen out a plurality of first-category abnormal pressure data and second-category abnormal pressure data of the target cutting arm during the operation cycle based on each pressure growth rate; wherein the first-category abnormal pressure data refers to a sudden increase in pressure caused by random factors, and the second-category abnormal pressure data refers to insufficient pressure caused by specific abnormal conditions; Determine the second abnormal index of the target soil cutting arm in the operation cycle according to a plurality of first-class abnormal pressure data of the target soil cutting arm in the operation cycle, the collection time of the first-class abnormal pressure data and the second-class abnormal pressure data, and a plurality of first-class abnormal pressure data of each comparison soil cutting arm in the operation cycle; wherein the comparison soil cutting arm is the soil cutting arm other than the target soil cutting arm; The single operation abnormality factor of the target soil cutting arm is determined by combining the first abnormality index and the second abnormality index of each operation cycle of the target soil cutting arm.

[0006] Furthermore, the determining of the first abnormal index of the target cutting arm in the operation cycle includes: According to the pressure data sequence and resistance data sequence corresponding to any operation cycle of the target cutting arm, a pressure resistance scatter plot corresponding to the operation cycle of the target cutting arm is obtained; Performing linear fitting on the pressure-resistance scatter plot to obtain the linear fitting degree between the pressure and resistance of the target cutting arm in the operation cycle; The linear fit is subjected to negative correlation processing to obtain the first abnormality index of the target cutting arm in the operation cycle.

[0007] Furthermore, the second abnormality indicator of the target cutting arm in the operation cycle is determined, including: According to the collection time of multiple first-type abnormal pressure data and second-type abnormal pressure data of the target cutting arm in the operation cycle, determine the maximum time interval corresponding to two second-type abnormal pressure data, and determine the maximum continuous duration of continuously distributed first-type abnormal pressure data; The acquisition time of multiple first-type abnormal pressure data of the target cutting arm in the operation cycle is used as the target acquisition time, and the pressure data of each comparison cutting arm at each target acquisition time is determined as the comparison data; Determine the abnormal degree of the first type of abnormal pressure data of the target soil cutting arm according to the difference between the first type of abnormal pressure data of the target soil cutting arm and the comparison data of each comparison soil cutting arm at the same target acquisition time; The second abnormality index of the target cutting arm in this operation cycle is determined by combining the maximum time interval, the maximum continuous duration and the abnormality degree of the first type of abnormal pressure data.

[0008] Further, the determining of the abnormal degree of the first type of abnormal pressure data of the target cutting arm includes: Calculate the average of the comparison data of all comparison cutting arms under the same target collection time; Determine the absolute value of the difference between the first type of abnormal pressure data of the target cutting arm and the average value of the comparison data at the same target acquisition time; The average value of the absolute values ​​of the differences corresponding to all target acquisition times is taken as the abnormality degree of the first type of abnormal pressure data of the target cutting arm.

[0009] Furthermore, the combining the first abnormality index and the second abnormality index of each operation cycle of the target soil cutting arm to determine the single operation abnormality factor of the target soil cutting arm includes: Adding the first abnormality index and the second abnormality index of the same operation cycle, and using the added result as a single operation abnormality comparison value of the target cutting arm corresponding to the operation cycle; The single operation abnormality comparison value of each operation cycle of the target cutting arm is obtained, and the maximum single operation abnormality comparison value is used as the single operation abnormality factor of the target cutting arm.

[0010] Furthermore, the determination step of S3 includes: Perform STL decomposition on the pressure data series corresponding to different operation cycles of the target cutting arm to obtain the trend item; For each trend item, the sequence consisting of the maximum value in the trend item and all the data before the maximum value is taken as the target sequence; the sequence consisting of the maximum value in the trend item and all the data after the maximum value is taken as the reference sequence; Calculate the standard deviation of the target sequence corresponding to each operation cycle of the target soil cutting arm, and determine the first continuous operation abnormality index of the target soil cutting arm according to the difference between the standard deviation of a single operation cycle of the target soil cutting arm and other operation cycles; Determine the second continuous operation abnormality index of the target soil cutting arm according to the change rate of the reference sequence corresponding to each operation cycle of the target soil cutting arm; Obtain the maximum pressure in the pressure data sequence corresponding to different operation cycles of the target cutting arm, and calculate the coefficient of variation of the maximum pressure corresponding to all operation cycles of the target cutting arm as the third continuous operation abnormality indicator of the target cutting arm; The continuous operation abnormality factor of the target soil cutting arm is determined by combining the first continuous operation abnormality index, the second continuous operation abnormality index and the third continuous operation abnormality index of the target soil cutting arm.

[0011] Furthermore, the determining of the first continuous operation abnormality index of the target soil cutting arm according to the difference between the standard deviation of the single operation cycle of the target soil cutting arm and other operation cycles includes: Taking any operation cycle of the target cutting arm as the target operation cycle, calculating the absolute value of the difference between the standard deviation of the target operation cycle and the standard deviations of other operation cycles except the target operation cycle; The average value of the absolute values ​​of the differences between the standard deviations of all operation cycles is used as the first continuous operation abnormality indicator of the target cutting arm.

[0012] Furthermore, the determination step of S4 includes: Calculate the product of the single operation abnormality factor and the continuous operation abnormality factor of the same soil cutting arm, normalize the product of the two abnormality factors, and obtain the operation abnormality degree of each soil cutting arm; Calculate the ratio of the number of second-type abnormal pressure data to the number of all pressure data in each operation cycle of each cutting arm, and take the average of the ratios of all operation cycles as the abnormal weight of the corresponding cutting arm; A weighted average process is performed according to the operation abnormality degree of each cutting arm and the abnormality weight to obtain the comprehensive fault degree of the garden excavator to be monitored.

[0013] The present invention has the following beneficial effects: The present invention provides a monitoring method for automated tree transplantation equipment of a garden excavating machine, which obtains pressure data and resistance data corresponding to each operation cycle of a soil cutting arm, which are basic data for monitoring and analyzing the soil cutting arm, and the monitoring and analysis of the soil cutting arm are the key to improving the efficiency and safety of garden excavating and planting; since a complete operation cycle of the soil cutting arm is a basic unit for analyzing the state and performance of the machine, the operation data of each operation cycle is divided into a sequence, which is helpful for more accurate analysis and understanding of various phenomena in the excavation process and their influence on the state of the machine; by processing the data of single and multiple operation cycles, a single operation abnormality factor and a continuous operation abnormality factor are determined, and then the operation abnormality factors determined by the two aspects are combined to obtain a comprehensive fault degree, and the efficiency of a single operation cycle can be optimized through the comprehensive fault degree, and it is ensured that each operation step is based on actual data feedback, which is helpful for improving the survival rate of tree planting; compared with the existing soil cutting arm monitoring method, the present invention can identify potential fault trends by tracking the performance changes of the equipment for a long time, can prevent unexpected faults, reduce downtime, extend the life of the equipment, and reduce long-term maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 A flowchart of a method for monitoring automated tree transplanting equipment of a garden excavating machine according to an embodiment of the present invention; Figure 2 This is a flowchart for implementing step S2 in an embodiment of the present invention; Figure 3 This is a flowchart for implementing step S203 in an embodiment of the present invention; Figure 4 Flow chart for implementing step S3 in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0017] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0018] The application scenarios targeted by the present invention may be: When implementing operation status monitoring, the tree transplantation automation equipment used for garden excavation only performs status analysis based on the current operation data. This has analysis limitations, strong dependence on data quality, and neglect of environmental impacts. As a result, the accuracy of the cutting arm operation status monitoring results is low, which may lead to operational errors of the garden excavation machinery, thereby affecting the survival rate of trees after planting.

[0019] In order to ensure the continuous operation and working efficiency of the soil cutting arm and improve the survival rate of trees after planting, an embodiment of the present invention provides a tree transplanting automation equipment monitoring method for a garden excavator, such as Figure 1 As shown, the following steps are included: S1, obtaining a pressure data sequence and a resistance data sequence corresponding to each operation cycle of a plurality of soil cutting arms of the garden excavator to be monitored in the current period.

[0020] First of all, it should be noted that during the operation of the excavator, a complete operation cycle of the cutting arm is the basic unit for analyzing the mechanical state and performance. The cutting arm is the movable arm of the cutting bucket. In addition, obtaining the data segments corresponding to each operation cycle in the current period will help to more accurately analyze and understand the influence of various phenomena and their mechanical states during the excavation process. Under the same operating conditions, the pressure of the cutting arm is the same as the resistance trend during operation. If there is a problem in the operation due to a machine failure, the cutting arm may not reach the corresponding pressure condition due to the drive, so it is necessary to obtain pressure data and resistance data for subsequent equipment operation status analysis.

[0021] Specifically, in the current time period, when analyzing the operating status of each cutting arm of the garden excavation machinery to be monitored during each operation cycle during the excavation operation, the pressure data and resistance data are collected through the multi-dimensional sensor installed on the hydraulic rod; when dividing the time series data sequence corresponding to a single operation cycle, the division is performed using the zero point values ​​in the current time period as the dividing points, and one time series data sequence corresponds to one operation cycle. Among them, each operation cycle has its corresponding pressure data sequence and resistance data sequence, the data collection frequency is once per second, and the collection time is 1 hour. The collection frequency and collection time can be set by the implementer according to the specific actual situation, and are not specifically limited.

[0022] In addition, it is worth mentioning that, considering the range of motion and working conditions of the hydraulic rod, a stable installation scheme that will not affect the normal operation of the hydraulic rod is designed. According to the designed installation scheme, the multi-dimensional sensor is installed on the hydraulic rod of the movable arm of each cutting arm, ensuring that all connections are firm and reliable, and the sensor cables or wireless transmission equipment are properly protected and managed. The sensor is connected to the data acquisition system, which can be a dedicated data logger or an interface device connected to a computer.

[0023] So far, this embodiment has obtained the pressure data sequence and the resistance data sequence corresponding to each operation cycle of each cutting arm.

[0024] S2, determining a single operation abnormality factor of each soil cutting arm according to the pressure data sequence and the resistance data sequence corresponding to each soil cutting arm in the same operation cycle.

[0025] First of all, it should be noted that blockage and leakage are the main reasons for low pressure when the equipment is working, and low pressure will directly lead to slow lifting or weak rotation of the cutting arm, which will affect the effect of tree planting. If the hydraulic system leaks, the hydraulic oil that should maintain continuous pressure cannot be stabilized, resulting in inconsistent force of the cutting arm during operation, which manifests as shaking or unstable movement. Therefore, by analyzing the abnormal evaluation of each cutting arm in a single operation and the coordination between multiple cutting arms, the abnormal condition of the machinery can be further analyzed, that is, the abnormal factor of the single operation of the cutting arm can be quantified.

[0026] The above step S2 can be Figure 2 The steps S201 to S204 shown implement: S201, taking any soil cutting arm as the target soil cutting arm, analyzing the difference in the changing trend between pressure and resistance according to the pressure data sequence and resistance data sequence corresponding to any operation cycle of the target soil cutting arm, and determining the first abnormal indicator of the target soil cutting arm in the operation cycle.

[0027] Here, any cutting arm is taken as an example to analyze the abnormal factors of a single operation, and any cutting arm is recorded as the target cutting arm. The calculation process of the first abnormal index of each operation cycle of other cutting arms can refer to the same steps. The first abnormal index is determined by analyzing the difference in the change trend between pressure and resistance in a single operation cycle. The larger the first abnormal index, the more serious the operation abnormality of the target cutting arm in this operation cycle.

[0028] During a single operation, the pressure change of each cutting arm should gradually increase with the increase of resistance. If the soil quality is uniform during a single operation, the resistance change is consistent, and the pressure change rate of each cutting arm is also relatively consistent. If there is a large pressure mutation at a certain place, but other changes are still relatively consistent, it may be due to special circumstances such as encountering stones during the operation, causing a sudden change in the mechanical pressure of a certain cutting arm, which is still normal. However, if the mutation is maintained at a certain level for a long time, it may be due to a failure of the machine itself, causing damage to the pressure system and unable to provide normal pressure maintenance. Therefore, combined with the changes in the pressure resistance data of a single operation cycle of the cutting arm, the first abnormal indicator of the target cutting arm in this operation cycle can be quantified.

[0029] As an example, the above step S201 may be implemented through steps S211 to S231 (not shown in the figure): S211, according to the pressure data sequence and the resistance data sequence corresponding to any operation cycle of the target cutting arm, a pressure-resistance scatter plot corresponding to the operation cycle of the target cutting arm is obtained.

[0030] Specifically, the resistance is used as the data on the horizontal axis, and the pressure is used as the data on the vertical axis to obtain a pressure resistance scatter plot corresponding to the target cutting arm in this operation cycle. The process of obtaining the scatter plot is a prior art and is not within the scope of protection of the present invention, and will not be elaborated on in detail here.

[0031] S221, performing linear fitting on the pressure-resistance scatter plot to obtain the linear fitting degree between the pressure and resistance of the target cutting arm in this operation cycle.

[0032] Specifically, all data points in the pressure resistance scatter plot are fitted to obtain the linear fit of the fitted line. The implementation process of the straight line fitting is a prior art and is not within the scope of protection of the present invention, and will not be elaborated on in detail here.

[0033] It should be noted that the greater the linear fitting degree, the better the correlation between the pressure and resistance changes of the target cutting arm in this operation cycle, that is, the more consistent the changing trends of pressure and resistance are, and the smaller the possibility of abnormal operation of the target cutting arm in this operation cycle is.

[0034] S231, performing negative correlation processing on the linear fitting degree to obtain the first abnormality index of the target cutting arm in this operation cycle.

[0035] In this embodiment, since there is a negative correlation between the linear fit and the abnormal operation of a single operation cycle of the target cutting arm, the larger the linear fit, the stronger the correlation between the pressure and resistance in the operation cycle, and the smaller the possibility of abnormality, so it is necessary to perform negative correlation processing on the linear fit.

[0036] Specifically, exp (-) is used to implement negative correlation processing on the linear fit, and the linear fit after negative correlation processing is used as the first abnormal indicator of the target cutting arm in this operation cycle. Of course, the implementer can also implement negative correlation processing by taking the inverse or other methods.

[0037] S202, determining each pressure growth rate of the target cutting arm during the operation cycle from the beginning to the full load, and screening out a plurality of first-category abnormal pressure data and second-category abnormal pressure data of the target cutting arm during the operation cycle based on each pressure growth rate.

[0038] First, determine the pressure growth rates of the target cutting arm from the beginning to full load during this operation cycle.

[0039] Here, the earth-cutting arm from start to full load refers to the process from start to bottom to clamping in the whole operation cycle of the earth-cutting arm. Downward refers to the process of inserting into the soil. Only the relevant data of this part are analyzed because it can truly show the operating status of the earth-cutting arm during the actual operation process. It can also reduce the amount of data to a certain extent and improve the efficiency of data analysis.

[0040] As an example, the calculation formula for the pressure growth rate at the i-th moment can be: ; In the formula, represents the pressure growth rate at the i-th moment, represents the pressure data at the i+1th moment, Represents the pressure data at the i-th moment.

[0041] In the calculation formula of the pressure growth rate, the larger the pressure data at the i+1th moment is relative to the pressure data at the i-th moment, the greater the pressure growth rate at the i-th moment; the pressure growth rate is used to measure the growth of the pressure data at each moment, which can represent the change of the pressure data; the pressure growth rate at each moment is obtained to facilitate the subsequent screening of abnormally growing pressure data, that is, the pressure growth rate is an indicator for subsequent screening of abnormally growing pressure data; for the last moment in the pressure data sequence, this embodiment directly assigns the pressure growth rate of the last moment in the sequence to zero.

[0042] Of course, implementers can also use other methods to determine the pressure growth rate, such as or , this embodiment does not limit the method for determining the pressure growth rate.

[0043] It should be noted that, under normal circumstances, the pressure data at each moment corresponding to each operating cycle does not equal zero. If there is an extreme case, a hyperparameter is added to the denominator of the fraction, and the hyperparameter can be set to 0.1.

[0044] Secondly, a plurality of first-type abnormal pressure data and second-type abnormal pressure data of the target cutting arm in the operation cycle are screened out based on each pressure growth rate.

[0045] Here, the first type of abnormal pressure data includes pressure data caused by a sudden increase due to random conditions, that is, the first type of abnormal pressure data refers to a sudden increase in pressure caused by random factors, and the second type of abnormal pressure data includes pressure data lacking due to abnormal conditions, that is, the second type of abnormal pressure data is insufficient pressure due to specific abnormal conditions. Random conditions can be affected by environmental factors, and the first type of abnormal pressure data and the second type of abnormal pressure data are screened out by using the pressure growth rate in combination with the data properties of the first type of abnormal pressure data and the second type of abnormal pressure data.

[0046] Specifically, after calculating the average value of all pressure growth rates, add three times the standard deviation of all pressure growth rates as the first judgment threshold, and the pressure data at the corresponding moment when the pressure growth rate is greater than the first judgment threshold is regarded as the first type of abnormal pressure data; after calculating the average value of all pressure growth rates, subtract three times the standard deviation of all pressure growth rates as the second judgment threshold, and the pressure data at the corresponding moment when the pressure growth rate is less than the second judgment threshold is regarded as the second type of abnormal pressure data.

[0047] It should be noted that data distribution often follows a normal distribution (or approximates a normal distribution), where the vast majority of data points are concentrated near the mean, and the frequency of data points gradually decreases as the distance from the mean increases. In order to identify abnormal data points (also called outliers), the relationship between the mean and the standard deviation is usually used, because this can help determine which data points deviate from the normal distribution range, which may be caused by incorrect measurements, extreme external factors, or extreme system conditions; the first type of abnormal pressure data is located at the right tail of the distribution and is extremely large. The second type of abnormal pressure data is located at the left tail of the distribution and is extremely small, which usually indicates that the system may have some negative anomalies, such as data loss, extreme negative impact, or measurement errors. Such abnormal points also need attention because they may cause abnormal behavior or potential failures of the system.

[0048] In addition, it is worth explaining that when the second type of abnormal pressure data does not exist in the sequence, it means that the target cutting arm has no abnormality caused by the equipment itself during this operation cycle, and a value of 0.0001 can be directly assigned, which means that there is no need to over-analyze the operating status of the target cutting arm during this operation cycle.

[0049] S203, determining the second abnormal index of the target earth cutting arm in this operation cycle according to multiple first-category abnormal pressure data of the target earth cutting arm in this operation cycle, the collection time of the first-category abnormal pressure data and the second-category abnormal pressure data, and multiple first-category abnormal pressure data of each comparison earth cutting arm in this operation cycle.

[0050] Here, the second abnormal index is determined by analyzing the abnormal degree of the abnormal pressure data. The larger the time difference between the second type of abnormal pressure data, the longer the equipment abnormality lasts, the greater the abnormal degree of the abnormal pressure data, and the larger the second abnormal index; for each cutting arm of the excavator, each cutting arm has a different state of clamping the tree, and the abnormal condition is determined by analyzing the pressure changes of all cutting arms under the same resistance in the same operation cycle.

[0051] As an example, the above step S203 can be performed by Figure 3 The steps S213 to S243 shown implement: S213, according to the collection time of multiple first-type abnormal pressure data and second-type abnormal pressure data of the target cutting arm in this operation cycle, determine the maximum time interval corresponding to two second-type abnormal pressure data, and determine the maximum continuous duration of continuously distributed first-type abnormal pressure data.

[0052] In this embodiment, from all the second-category abnormal pressure data corresponding to the operating cycle of the target cutting arm, the first second-category abnormal pressure data and the last second-category abnormal pressure data are selected in chronological order, and the collection times of the two selected second-category abnormal pressure data are determined, and then the maximum time interval is determined; from all the first-category abnormal pressure data corresponding to the operating cycle of the target cutting arm, the continuous duration of each continuously distributed first-category abnormal pressure data is determined, and then the maximum continuous duration is determined.

[0053] S223, taking the collection time of a plurality of first-type abnormal pressure data of the target cutting arm in the operation cycle as the target collection time, and determining the pressure data of each comparison cutting arm at each target collection time as comparison data.

[0054] If one cutting arm shows an abnormal pressure drop or unstable pressure fluctuation relative to other cutting arms, it means that the degree of abnormality is greater. For example, at the first type of abnormal pressure data with a larger growth rate, only the growth rate of a single cutting arm changes suddenly, and the maintenance time is short, which means that the cutting arm is more likely to be normal. The longest continuity of the first type of abnormal pressure data in time is short, and it is more likely to be normal operation. At the same time, the consistency of pressure changes between multiple cutting arms is analyzed, and the abnormal situation of the machine is further reflected through the synergy between multiple cutting arms. In order to realize the comparative analysis between the above-mentioned different cutting arms, the target cutting arm is used as the benchmark to analyze the difference in pressure data between the target cutting arm and other cutting arms except the target cutting arm.

[0055] In this embodiment, the collection time of multiple first-category abnormal pressure data in the operation cycle of the cutting arm is determined and recorded as the target collection time; the pressure data corresponding to the target collection time is determined in the pressure data sequences of other cutting arms as comparison data.

[0056] S233, determining the abnormality degree of the first type of abnormal pressure data of the target soil cutting arm according to the difference between the first type of abnormal pressure data of the target soil cutting arm and the comparison data of each comparison soil cutting arm at the same target acquisition time.

[0057] In this embodiment, the greater the difference between the first type of abnormal pressure data of the target soil cutting arm at the same target acquisition time and each comparison data, the less similar the operating state of the target soil cutting arm is with the comparison soil cutting arm at the same acquisition time, and the greater the degree of abnormality of the first type of abnormal pressure data of the target soil cutting arm at the target acquisition time.

[0058] Specifically, the average value of the comparison data of all comparison cutting arms under the same target acquisition time is calculated; the absolute value of the difference between the first type of abnormal pressure data of the target cutting arm and the average value of the comparison data under the same target acquisition time is determined; and the average value of the absolute values ​​of the difference corresponding to all target acquisition times is taken as the abnormality degree of the first type of abnormal pressure data of the target cutting arm.

[0059] S243, determining a second abnormality indicator of the target cutting arm in this operation cycle by combining the maximum time interval, the maximum continuous time, and the abnormality degree of the first type of abnormal pressure data.

[0060] As an example, the calculation formula of the second abnormality index of the target cutting arm in this operation cycle can be: ; In the formula, Indicates the second abnormal index of the target cutting arm in this operation cycle. Indicates the abnormal degree of the first type of abnormal pressure data of the target cutting arm, Indicates the collection time of the last second-type abnormal pressure data corresponding to the target cutting arm in this operation cycle, Indicates the time when the first second-type abnormal pressure data corresponding to the target cutting arm in this operation cycle is collected. Indicates the maximum time interval, Indicates the maximum continuous duration.

[0061] In the calculation formula of the second abnormal index, the abnormal degree of the first type of abnormal pressure data , Maximum time interval , Maximum continuous duration They are positively correlated with the second abnormal index. The abnormal degree of the first type of abnormal pressure data , Maximum time interval And the maximum continuous duration The larger the value, the larger the second abnormality index. In addition, it is worth noting that when calculating the second abnormality index, the units of different calculation factors may be different, but this embodiment only performs data analysis on the numerical value itself without considering the unit effect.

[0062] It should be noted that, when calculating the second abnormal index, the maximum time interval of the second type of abnormal pressure data is the main factor in quantifying the degree of abnormality in the operating status of the operation cycle. The larger the maximum time interval of the second type of abnormal pressure data, the longer the duration of the abnormal pressure data generated by the equipment failure itself. The maximum continuous duration and the degree of abnormality of the first type of abnormal pressure data are to supplement the complete equipment failure. To a certain extent, it can correct the influence of external factors such as the environment on the second type of abnormal pressure data, and improve the calculation accuracy and reliability of the second abnormal index.

[0063] S204, determining a single operation abnormality factor of the target soil cutting arm by combining the first abnormality index and the second abnormality index of each operation cycle of the target soil cutting arm.

[0064] Specifically, the first abnormality index and the second abnormality index of the same operation cycle are added, and the result of the addition is used as the single operation abnormality comparison value of the target cutting arm corresponding to the operation cycle; the single operation abnormality comparison value of each operation cycle of the target cutting arm is obtained, and the maximum single operation abnormality comparison value is used as the single operation abnormality factor of the target cutting arm. With reference to the calculation process of the single operation abnormality factor of the target cutting arm, the single operation abnormality factor of each cutting arm can be obtained, which will not be described again here.

[0065] It should be noted that the larger the first abnormal index representing the linear fit of the pressure resistance in a single operation cycle, the greater the difference in the trend change of the pressure resistance and the larger the single operation abnormality factor; the larger the second abnormal index representing the degree of abnormality of the abnormal data in a single operation cycle, the more likely it is that the hydraulic system is improperly adjusted or a fault has occurred.

[0066] So far, this embodiment has obtained the single operation abnormality factor of each cutting arm.

[0067] S3, determining the continuous operation abnormality factor of each soil cutting arm according to the pressure data sequence corresponding to different operation cycles of the same soil cutting arm.

[0068] First of all, it should be noted that when the earth-cutting arm is working, a single operation may expose some problems or deficiencies of the equipment, and these problems may become more obvious in multiple operations. Therefore, the analysis of pressure data from multiple operations is helpful to discover and solve equipment failure problems and promote equipment maintenance and upgrades. It is often also a multiple continuous operation. If the situation is normal, the pressure change trend of the earth-cutting arm under multiple operations is the same in the operation process with similar construction conditions.

[0069] As an example, the above step S3 can be Figure 4 The steps S31 to S36 shown implement: S31, performing STL decomposition on the pressure data sequence corresponding to different operation cycles of the target cutting arm to obtain a trend item.

[0070] In this embodiment, the trend item represents the main change trend of the whole process. The more consistent the change trend between each operation, the greater the normal condition. If there is a fault, such as leakage, there will be differences between trend items after the leakage occurs, and the differences will only increase or decrease gradually, which is specifically manifested as the abnormality gradually increasing, the abnormality aggravating or unchanged. Therefore, it is necessary to obtain the trend item of the pressure data sequence corresponding to each operation cycle.

[0071] Among them, the implementation process of STL (Seasonal-Trend decomposition procedure based on Loess, time series decomposition algorithm) decomposition is a prior art, which is not within the protection scope of the present invention and will not be elaborated here.

[0072] S32, for each trend item, a sequence consisting of the maximum value in the trend item and all data before the maximum value is used as a target sequence; a sequence consisting of the maximum value in the trend item and all data after the maximum value is used as a reference sequence.

[0073] In this embodiment, determining the target sequence is used to subsequently identify the peak value in the time series (the maximum value in the trend item) and the evolution process of the data before the peak value; in addition, determining the target sequence and the reference sequence helps to clarify the significant differences in the data before and after the fault occurs, and provides data support for the subsequent determination of the first continuous operation abnormality indicator and the second continuous operation abnormality indicator.

[0074] It is worth noting that if there are multiple identical maximum values ​​in a trend item, the last maximum value with a later collection time will be taken.

[0075] S33, calculating the standard deviation of the target sequence corresponding to each operation cycle of the target soil cutting arm, and determining the first continuous operation abnormality index of the target soil cutting arm according to the difference between the standard deviation of a single operation cycle of the target soil cutting arm and other operation cycles.

[0076] In this embodiment, under normal circumstances, the closer the standard deviation of the target sequence corresponding to each operation cycle is, the higher the consistency and stability of the pressure change trend between multiple operations. Therefore, the greater the difference in the standard deviation of the target sequence between a single operation cycle of the target cutting arm and other operation cycles, the worse the consistency and stability of the pressure change trend between multiple operations, and the larger the first continuous operation abnormality index will be.

[0077] As an example, the step of determining the first continuous operation abnormality indicator of the target cutting arm may include: In the first step, any operation cycle of the target cutting arm is taken as the target operation cycle, and the absolute value of the difference between the standard deviation of the target operation cycle and the standard deviation of other operation cycles except the target operation cycle is calculated.

[0078] In the second step, the average of the absolute values ​​of the differences between the standard deviations of all operation cycles is used as the first continuous operation abnormality indicator of the target cutting arm.

[0079] Among them, the standard deviation of the target operation cycle is the standard deviation of the pressure data sequence corresponding to the target operation cycle, which can be used to measure the fluctuation degree of the pressure data sequence. Of course, in addition to the calculation method of the standard deviation, the pressure fluctuation degree can also be quantified by calculating the variance of the pressure data sequence.

[0080] S34, determining a second continuous operation abnormality index of the target soil cutting arm according to the change rate of the reference sequence corresponding to each operation cycle of the target soil cutting arm.

[0081] In this embodiment, under normal circumstances, the level of full load during multiple operations should be consistent, so the second continuous operation abnormality index of the target cutting arm can be quantified based on the change rate of the reference sequence.

[0082] Specifically: the reference sequence is mapped to a two-dimensional coordinate system, with the horizontal axis representing the acquisition time and the vertical axis representing the data in the reference sequence. A straight line fit is performed on all data points on the coordinate system, and the average value of the slope of the fitting straight line corresponding to all operation cycles is used as the second continuous operation abnormality indicator of the target cutting arm.

[0083] S35, obtaining the maximum pressure in the pressure data sequence corresponding to different operation cycles of the target cutting arm, and calculating the coefficient of variation of the maximum pressure corresponding to all operation cycles of the target cutting arm as the third continuous operation abnormality indicator of the target cutting arm.

[0084] In this embodiment, the coefficient of variation can measure the relative volatility of the data. The smaller the coefficient of variation, the smaller the overall variation, and thus the better the stability of the peak point. A maximum value is selected from each pressure data sequence as the maximum pressure value, the mean and standard deviation of all the maximum pressure values ​​are calculated, and the ratio of the standard deviation to the mean is used as the coefficient of variation, thereby obtaining the third continuous operation abnormality index of the target cutting arm.

[0085] S36, determining a continuous operation abnormality factor of the target soil cutting arm by combining the first continuous operation abnormality index, the second continuous operation abnormality index and the third continuous operation abnormality index of the target soil cutting arm.

[0086] As an example, the calculation formula of the continuous operation abnormality factor of the target cutting arm can be: ; In the formula, Indicates the continuous operation abnormality factor of the target cutting arm, It represents the abnormal index of the second continuous operation of the target cutting arm, and also represents the slope mean of the reference sequence corresponding to all operation cycles. V represents the total number of operation cycles. represents the standard deviation of the target sequence corresponding to the vth operation cycle, Represents the average value of the standard deviation of the target sequence corresponding to all sub-operation cycles, Indicates the first continuous operation abnormality index of the target cutting arm, represents the absolute value function, Indicates the third continuous operation abnormality index of the target cutting arm.

[0087] In the calculation formula of the continuous operation abnormality factor, with regard to obtaining the mean slope of the reference sequence corresponding to all sub-operation cycles, a straight line fitting is first performed on the reference sequence, and then the slope of the fitting line is determined. The mean of all slopes is used as the second continuous operation abnormality index to characterize the change rate of the reference sequence. It represents the absolute value of the difference between the standard deviation of the target sequence corresponding to each operation cycle and the average value of the standard deviation of the target sequence corresponding to all sub-operation cycles. , all operation cycles can include the vth operation cycle.

[0088] It should be noted that when analyzing the continuous operation abnormality factor of the target cutting arm under multiple consecutive operation cycles, quantifying the abnormal operation of the cutting arm from three different aspects can more comprehensively analyze some problems or deficiencies of the cutting arm equipment, thereby improving the numerical accuracy of the continuous operation abnormality factor.

[0089] So far, this embodiment has obtained the continuous operation abnormality factor of each cutting arm.

[0090] S4, combining the single operation abnormality factor and the continuous operation abnormality factor of each cutting arm to determine the comprehensive fault degree of the garden excavator to be monitored.

[0091] Here, the comprehensive fault degree refers to an indicator that can help evaluate the operational stability and reliability of the earth-cutting arm in long-term operations. Combining the comprehensive fault degrees determined by the two aspects can, to a certain extent, reduce the analysis limitations, strong dependence on data quality, and the influence of neglecting environmental factors on the accuracy of fault detection, thereby improving the survival rate of trees after planting.

[0092] The above step S4 can be implemented through steps S41 to S43 (not shown in the figure): S41, calculating the product of the single operation abnormality factor and the continuous operation abnormality factor of the same soil cutting arm, normalizing the product of the two abnormality factors, and obtaining the operation abnormality degree of each soil cutting arm.

[0093] In this embodiment, the two abnormal factors are combined to obtain the operation abnormality degree of the comprehensive analysis of the operation difference of different cutting arms in the same operation cycle and the operation change trend of a single cutting arm in multiple consecutive operation cycles. Each cutting arm has its corresponding operation abnormality degree. Among them, the normalization processing can limit the value range of the operation abnormality degree to between 0 and 1, which can be achieved using the norm function.

[0094] It should be noted that the operation abnormality degree can help evaluate the stability and reliability of the earth-cutting arm in long-term operation. If the abnormality degree in a single operation is high, or the abnormality continuity in multiple operations is strong, then the operation abnormality degree of the earth-cutting arm will be greater, thus occupying a more important position in the comprehensive evaluation, which indicates that the earth-cutting arm has a higher abnormal risk and requires special attention.

[0095] S42, calculating the ratio of the number of second-type abnormal pressure data to the number of all pressure data in each operation cycle of each soil cutting arm, and taking the average of the ratios of all operation cycles as the abnormal weight of the corresponding soil cutting arm.

[0096] In this embodiment, the various cutting arms of the same garden excavator have different effects on equipment failure during operation, and the abnormal weight can represent the actual contribution of the operation abnormality of the cutting arm to the overall failure. Specifically, the greater the difference between the number of second-type abnormal pressure data in a single operation cycle and the number of all pressure data in the corresponding operation cycle, the smaller the possibility of abnormal operation data when the corresponding cutting arm is operating in the current period, and the smaller the actual contribution to the overall failure.

[0097] It should be noted that the first type of abnormal pressure data includes sudden increases caused by random situations, and the second type of abnormal pressure data includes lack of pressure caused by abnormalities. The second type of abnormal pressure data is more likely to be data generated by real equipment abnormalities. Therefore, when calculating the abnormal weight, only the second type of abnormal pressure data is analyzed.

[0098] S43, performing weighted averaging processing according to the operation abnormality degree and abnormality weight of each soil cutting arm to obtain the comprehensive fault degree of the garden excavator to be monitored.

[0099] After obtaining the operation abnormality degree and abnormality weight of each cutting arm, the operation abnormality degrees of all the cutting arms are combined together using the weighted average calculation method to determine whether there is a fault in the garden excavation machinery to be monitored, that is, to determine the comprehensive fault degree of the garden excavation machinery to be monitored.

[0100] So far, this embodiment has obtained the comprehensive fault degree of the garden excavator to be monitored.

[0101] S5, monitor the condition of garden excavation machinery based on the comprehensive fault degree.

[0102] In this embodiment, a fault determination threshold is set. When the comprehensive fault degree is greater than the fault determination threshold, it can be determined that the monitored garden excavator has a fault, and it is necessary to perform fault detection on the monitored garden excavator to eliminate the adverse effects of the mechanical fault. The monitored garden excavator can then perform tree planting operations after the fault, which can effectively improve the survival rate of tree planting. Among them, the fault determination threshold can be set to 0.7, and the implementer can set the size of the fault determination threshold according to the specific actual situation.

[0103] So far, this embodiment has completed the tree planting process of the garden excavator.

[0104] The present invention provides a monitoring method for automated tree transplantation equipment of a garden excavating machine, which obtains pressure data and resistance data corresponding to each operation cycle of a soil cutting arm, which are basic data for monitoring and analyzing the soil cutting arm, and the monitoring and analysis of the soil cutting arm are the key to improving the efficiency and safety of garden excavating and planting; since a complete operation cycle of the soil cutting arm is a basic unit for analyzing the state and performance of the machine, the operation data of each operation cycle is divided into a sequence, which is helpful for more accurate analysis and understanding of various phenomena in the excavation process and their influence on the state of the machine; by processing the data of single and multiple operation cycles, a single operation abnormality factor and a continuous operation abnormality factor are determined, and then the operation abnormality factors determined by the two aspects are combined to obtain a comprehensive fault degree, and the efficiency of a single operation cycle can be optimized through the comprehensive fault degree, and it is ensured that each operation step is based on actual data feedback, which is helpful for improving the survival rate of tree planting; compared with the existing soil cutting arm monitoring method, the present invention can identify potential fault trends by tracking the performance changes of the equipment for a long time, can prevent unexpected faults, reduce downtime, extend the life of the equipment, and reduce long-term maintenance costs.

[0105] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for monitoring automated tree transplanting equipment of a garden excavating machine, characterized in that: The following steps are involved: S1, obtaining the pressure data sequence and resistance data sequence corresponding to each operation cycle of several cutting arms of the garden excavator to be monitored in the current period; S2, determining a single operation abnormality factor of each soil cutting arm according to the pressure data sequence and resistance data sequence corresponding to each soil cutting arm in the same operation cycle; S3, determining the continuous operation abnormality factor of each soil cutting arm according to the pressure data sequence corresponding to different operation cycles of the same soil cutting arm; S4, combining the single operation abnormality factor of each soil cutting arm and the continuous operation abnormality factor to determine the comprehensive fault degree of the garden excavator to be monitored; S5, monitoring of the condition of garden excavation machinery based on the comprehensive fault degree; The determination step of S2 includes: Taking any soil cutting arm as the target soil cutting arm, analyzing the difference in the change trend between pressure and resistance according to the pressure data sequence and resistance data sequence corresponding to any operation cycle of the target soil cutting arm, and determining the first abnormal index of the target soil cutting arm in the operation cycle; Determine each pressure growth rate of the target cutting arm during the operation cycle from the beginning to full load, and screen out a plurality of first-category abnormal pressure data and second-category abnormal pressure data of the target cutting arm during the operation cycle based on each pressure growth rate; wherein the first-category abnormal pressure data refers to a sudden increase in pressure caused by random factors, and the second-category abnormal pressure data refers to insufficient pressure caused by abnormal conditions; Determine the second abnormal index of the target soil cutting arm in the operation cycle according to a plurality of first-class abnormal pressure data of the target soil cutting arm in the operation cycle, the collection time of the first-class abnormal pressure data and the second-class abnormal pressure data, and a plurality of first-class abnormal pressure data of each comparison soil cutting arm in the operation cycle; wherein the comparison soil cutting arm is the soil cutting arm other than the target soil cutting arm; Combining the first abnormal index and the second abnormal index of each operation cycle of the target soil cutting arm, determining the single operation abnormal factor of the target soil cutting arm; the determining the first abnormal index of the target soil cutting arm in the operation cycle includes: According to the pressure data sequence and resistance data sequence corresponding to any operation cycle of the target cutting arm, a pressure resistance scatter plot corresponding to the operation cycle of the target cutting arm is obtained; Performing linear fitting on the pressure-resistance scatter plot to obtain the linear fitting degree between the pressure and resistance of the target cutting arm in the operation cycle; Performing negative correlation processing on the linear fit degree to obtain the first abnormality index of the target cutting arm in the operation cycle; The second abnormal index of the target cutting arm in the operation cycle is determined, including: According to the collection time of multiple first-type abnormal pressure data and second-type abnormal pressure data of the target cutting arm in the operation cycle, determine the maximum time interval corresponding to two second-type abnormal pressure data, and determine the maximum continuous duration of continuously distributed first-type abnormal pressure data; The acquisition time of multiple first-type abnormal pressure data of the target cutting arm in the operation cycle is used as the target acquisition time, and the pressure data of each comparison cutting arm at each target acquisition time is determined as the comparison data; Determine the abnormal degree of the first type of abnormal pressure data of the target soil cutting arm according to the difference between the first type of abnormal pressure data of the target soil cutting arm and the comparison data of each comparison soil cutting arm at the same target acquisition time; Determine a second abnormality indicator of the target cutting arm in the operation cycle by combining the maximum time interval, the maximum continuous duration and the abnormality degree of the first type of abnormal pressure data; The calculation formula of the second abnormal index of the target cutting arm in this operation cycle is: ; In the formula, Indicates the second abnormal index of the target cutting arm in this operation cycle. Indicates the abnormal degree of the first type of abnormal pressure data of the target cutting arm, Indicates the collection time of the last second-type abnormal pressure data corresponding to the target cutting arm in this operation cycle, Indicates the time when the first second-type abnormal pressure data corresponding to the target cutting arm in this operation cycle is collected. Indicates the maximum time interval, Indicates the maximum continuous duration.

2. The method for monitoring tree transplanting automation equipment of a garden excavating machine according to claim 1, characterized in that: The step of determining the abnormality degree of the first type of abnormal pressure data of the target cutting arm comprises: Calculate the average of the comparison data of all comparison cutting arms under the same target collection time; Determine the absolute value of the difference between the first type of abnormal pressure data of the target cutting arm and the average value of the comparison data at the same target acquisition time; The average value of the absolute values ​​of the differences corresponding to all target acquisition times is taken as the abnormality degree of the first type of abnormal pressure data of the target cutting arm.

3. The method for monitoring tree transplanting automation equipment of a garden excavator according to claim 1, characterized in that: The step of combining the first abnormality index and the second abnormality index of each operation cycle of the target soil cutting arm to determine the single operation abnormality factor of the target soil cutting arm comprises: Adding the first abnormality index and the second abnormality index of the same operation cycle, and using the added result as a single operation abnormality comparison value of the target cutting arm corresponding to the operation cycle; The single operation abnormality comparison value of each operation cycle of the target cutting arm is obtained, and the maximum single operation abnormality comparison value is used as the single operation abnormality factor of the target cutting arm.

4. The method for monitoring tree transplanting automation equipment of a garden excavator according to claim 1, characterized in that: The determination step of S3 includes: Perform STL decomposition on the pressure data series corresponding to different operation cycles of the target cutting arm to obtain the trend item; For each trend item, the sequence consisting of the maximum value in the trend item and all the data before the maximum value is taken as the target sequence; the sequence consisting of the maximum value in the trend item and all the data after the maximum value is taken as the reference sequence; Calculate the standard deviation of the target sequence corresponding to each operation cycle of the target soil cutting arm, and determine the first continuous operation abnormality index of the target soil cutting arm according to the difference between the standard deviation of a single operation cycle of the target soil cutting arm and other operation cycles; Determine the second continuous operation abnormality index of the target soil cutting arm according to the change rate of the reference sequence corresponding to each operation cycle of the target soil cutting arm; Obtain the maximum pressure in the pressure data sequence corresponding to different operation cycles of the target cutting arm, and calculate the coefficient of variation of the maximum pressure corresponding to all operation cycles of the target cutting arm as the third continuous operation abnormality indicator of the target cutting arm; Determine the continuous operation abnormality factor of the target soil cutting arm by combining the first continuous operation abnormality index, the second continuous operation abnormality index and the third continuous operation abnormality index of the target soil cutting arm; The calculation formula of the abnormal factor of continuous operation of the target cutting arm is: ; In the formula, Indicates the continuous operation abnormality factor of the target cutting arm, It represents the abnormal index of the second continuous operation of the target cutting arm, and also represents the slope mean of the reference sequence corresponding to all operation cycles. V represents the total number of operation cycles. represents the standard deviation of the target sequence corresponding to the vth operation cycle, Represents the average value of the standard deviation of the target sequence corresponding to all sub-operation cycles, Indicates the first continuous operation abnormality index of the target cutting arm, represents the absolute value function, Indicates the third continuous operation abnormality index of the target cutting arm.

5. The method for monitoring tree transplanting automation equipment of a garden excavating machine according to claim 4, characterized in that: The first continuous operation abnormality index of the target cutting arm is determined, including: Taking any operation cycle of the target cutting arm as the target operation cycle, calculating the absolute value of the difference between the standard deviation of the target operation cycle and the standard deviations of other operation cycles except the target operation cycle; The average value of the absolute values ​​of the differences between the standard deviations of all operation cycles is used as the first continuous operation abnormality indicator of the target cutting arm.

6. The method for monitoring tree transplanting automation equipment of a garden excavator according to claim 1, characterized in that: The determination step of S4 includes: Calculate the product of the single operation abnormality factor and the continuous operation abnormality factor of the same soil cutting arm, normalize the product of the two abnormality factors, and obtain the operation abnormality degree of each soil cutting arm; Calculate the ratio of the number of second-type abnormal pressure data to the number of all pressure data in each operation cycle of each cutting arm, and take the average of the ratios of all operation cycles as the abnormal weight of the corresponding cutting arm; A weighted average process is performed according to the operation abnormality degree of each cutting arm and the abnormality weight to obtain the comprehensive fault degree of the garden excavator to be monitored.

Images