Forklift equipment state comprehensive evaluation method, device and system

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0044] The embodiment of the present invention discloses a method, device and system for comprehensive evaluation of the state of forklift equipment. The historical operation data of the forklift is acquired, and preprocessing and feature value extraction are performed on the historical operation data to obtain the description information of the state of the forklift equipment, and the state of the forklift equipment is Each dimension index in the description information is used as a feature vector, and multiple feature vectors are quantified and scored based on historical operating data to generate high-dimensional feature vectors, which are used as the overall health evaluation vector of forklifts. Each component of the high-dimensional feature vector Perform percentage weighted summation to obtain a percentage, and use the percentage as the overall health evaluation value of the forklift to comprehensively evaluate the state of the forklift equipment. When the present invention comprehensively evaluates the state of the forklift equipment, multiple dimensions are considered comprehensively, including: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, and driver operating conditions Therefore, a comprehensive evaluation of the operating status of forklifts can be realized, which not only solves the equipment status description information required for further equipment data analysis such as forklift maintenance, but also helps forklift manufacturing The supplier realizes the analysis of the long-term operation of the forklift, and then maintains and designs the auxiliary equipment to ensure the normal use of the forklift, prolong the service life of the forklift, and ensure the working efficiency of the forklift.

[0045] see figure 1, a flow chart of a method for comprehensive evaluation of forklift equipment status disclosed in an embodiment of the present invention, the method includes steps:

[0046] Step S101, obtaining the historical operation data of the forklift;

[0047] Among them, the historical operation data of the forklift includes: using the linear regression method to obtain the feedback torque current of the lifting motor, the speed of the lifting motor, the battery voltage, the current of the traveling motor and the speed of the traveling motor required by the forklift load;

[0048] The mechanism model is used to derive and calculate the lift cylinder pressure sensor data, acceleration sensor data, gyroscope sensor data, motor speed, etc. required for the forklift load.

[0049] Step S102, performing preprocessing and feature value extraction on the historical operation data to obtain the state description information of the forklift equipment;

[0050] The preprocessing of historical operating data mainly refers to: data cleaning of historical operating data, including: deleting irrelevant data and duplicate data in the original data set, smoothing noise data, screening out data irrelevant to the mining topic, and dealing with missing values ​​and abnormalities value etc.

[0051] It should be noted that the method or algorithm of each state description in the forklift equipment state description information can not only be applied to the feature value extraction of the forklift historical operation data, but also can be used for the feature value extraction of the forklift current operation condition.

[0052] Wherein, the forklift device state description information includes multiple dimension indicators, and the multiple dimension indicators include: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, and drive operation condition and any or all of the operating conditions of the motor.

[0053] Eigenvalue extraction is a method to transform the group measurement values ​​of a certain mode to highlight the representative characteristics of the mode.

[0054] In this embodiment, the state of the forklift equipment can be described from eight aspects. In practical applications, these eight aspects can be refined into multiple small eigenvalues. By combining these eigenvalues, the forklift equipment state can be realized. Comprehensive analysis, so that the evaluation of the state of the forklift is more comprehensive and prepared.

[0055] Below, the eight aspects of the description of the state of forklift equipment are introduced in detail, as follows:

[0056] 1) Forklift load

[0057] The load estimation of the forklift can be obtained by using the linear regression method of the historical operation data of the forklift or by deriving and calculating the mechanism model.

[0058] The linear regression method is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship between two or more variables.

[0059] ① The process of obtaining the forklift load by using the linear regression method on the historical operating data of the forklift is as follows:

[0060] The forklift load mass M is obtained by using the linear regression method on the historical operation data.

[0061] M=(h 1 , h 2 , h 3 , h 4 , h 5 )(x 1 ,x 2 ,x 3 ,x 4 ,x 5 ) T

[0062] Among them, h 1 Feedback torque current for lifting motor, h 2 is the lifting motor speed, h 3 is the battery voltage, h 4 is the walking motor current, h 5 is the travel motor speed, x 1 ,x 2 ,x 3 ,x 4 ,x 5 is the linear regression model parameter.

[0063] Among them, the parameter x 1 ,x 2 ,x 3 ,x 4 ,x 5 It can be obtained by performing linear regression on the historical operation data of the forklift.

[0064] Specifically, the least square method is used to learn and identify the historical operation data of forklifts input into the linear regression model, and the parameter x 1 ,x 2 ,x 3 ,x 4 ,x 5 , that is, the load M can be calculated according to the linear regression model.

[0065] It should be noted that parameter identification is a technology that combines theoretical models and experimental data for prediction. A set of parameter values ​​is determined according to experimental data and established models, so that the numerical results obtained by the model can be the best. Fit the test data.

[0066] The parameter identification ground push formula that the present invention adopts when learning identification is as follows:

[0067] K(m+1)=P(m)x(m+1)[1+x T (m+1)P(m)x(m+1)] -1;

[0068] P(m)=(x T (m)x(m)) -1;

[0069] P(m+1)=P(m)-K(m+1)x T (m+1)P(m);

[0070]

[0071] In the formula, x is the input of the forklift system, corresponding to h in the calculation formula of the forklift load mass M 1 ~ h 5 The value of , y is the output of the forklift system, corresponding to the forklift load mass M, m is the number of recursions, is the parameter estimate, K is the gain matrix, K(m+1) is the gain matrix under the m+1th recursion, P(m) is the intermediate process quantity, x(m+1) is the m+1th time System input under recursion, x T (m+1) is the transpose of the system input under the m+1th recursion, x T (m) is the transposition of the system input under the m-th recursion, x(m) is the system input under the m-th recursion, P(m+1) is the intermediate process quantity, is the estimated value of the parameter under the m+1th recursion, is the estimated value of the parameter under the mth recursion, and y(m+1) is the system output under the mth recursion.

[0072] Among them, after the forklift load corresponding to the forklift work data is determined, self-learning can be performed to correct the parameters. The forklift work data includes: h 1 Feedback torque current for lifting motor, h 2 is the lifting motor speed, h 3 is the battery voltage, h 4 is the walking motor current, h 5 is the travel motor speed, and the forklift load is the forklift load mass M.

[0073] ② The process of obtaining the forklift load by deriving and calculating the forklift load from the historical operation data of the forklift is as follows:

[0074] The forklift load calculation model is obtained by combining the historical operation data of the forklift and the operation mechanism of the forklift, and the forklift load is determined based on the load calculation model, specifically: the lifting dynamic model (F=ma) based on the forklift movement and the current based on the motor operation, The walking dynamics model established by the torque and rotational speed is used to obtain the forklift mechanism model; the forklift mechanism model is corrected to obtain the corrected mechanism model, and the forklift load calculation model is obtained based on the corrected mechanism model and historical operation data, and the forklift load is determined according to the forklift load calculation model .

[0075] Among them, the current, torque and rotational speed of the motor can be directly measured by the corresponding sensors. A lift cylinder pressure sensor and an acceleration sensor are installed on the forklift, and the acceleration sensor is used to measure the travel acceleration of the forklift.

[0076] The walking dynamics model is:

[0077] f q -f v v-f·sign(v)·M=Ma

[0078] f q =τR-f τ = kI q -f τ

[0079]

[0080] In the formula, M is the overall load of the vehicle body, a is the travel acceleration of the forklift, F q is the lift cylinder pressure, f v is the viscous friction coefficient of forklift driving, f is the sliding friction coefficient, f τ is the rotational friction coefficient of the motor, τ is the motor torque of the forklift, R is the radius of the forklift wheel, I q is the current, k is the model parameter, v is the running speed of the forklift, and sign(v) is a mathematical function calculation for v, specifically when x>0, sign(x)=1; when x=0, sign(x )=0; when x<0, sign(x)=-1.

[0081] The lift dynamics model is:

[0082] F-mg-f=ma, where the cylinder thrust is F=kI q or F=kP

[0083] The formula for calculating the load mass of the forklift is obtained by identifying the comprehensive friction coefficient f of the parameters and the model parameter k, and the model parameter k is a known quantity.

[0084] Based on the forklift mechanism model and the historical operation data of the forklift, the forklift load calculation model is obtained, and the forklift load calculation model is used to estimate the maximum load and the average load of the forklift in the preset time period, and the maximum load and the average load are used as the forklift in the forklift. Load conditions during the preset time period.

[0085] 2) Forklift working environment

[0086] ① The degree of vibration in the operating environment of the forklift;

[0087] The up and down acceleration measured by the acceleration sensor installed on the forklift is used as a measure of the degree of bumpiness in the operating environment of the forklift.

[0088] ② The slope of the running road;

[0089] The inclination angle measured by the gyroscope installed on the forklift is used as a measure of the slope of the running road.

[0090] ③Forklift running stability;

[0091] The fore-and-aft acceleration measured by the acceleration sensor installed on the forklift is used as a measure of whether the forklift is running smoothly.

[0092] ④Whether the forklift is reversing;

[0093] The motor keeps rotating forward while the forklift is moving forward. If the motor speed has a negative value, it indicates that the forklift driver is reversing during the handling process, which means that the working environment of the forklift is relatively narrow and there are places where it is impossible to turn.

[0094] ⑤The journey of a forklift to carry the goods;

[0095] Based on the lift motor current and the integral value of the motor speed, the distance for the forklift to carry the goods in one trip is determined. Specifically: integrating the travel motor speed between two adjacent lifting motor current peak values ​​to estimate the distance for a forklift to carry a cargo.

[0096] It should be noted that the working environment of the forklift includes but is not limited to the five situations listed above. In practical applications, the working environment of the forklift can be any one or a combination of several of the above five situations. It can also be based on the actual situation. Adding the determination conditions for the working environment of the forklift depends on actual needs, which is not limited in the present invention.

[0097] 3) Forklift power consumption

[0098] ① Electricity used by the forklift;

[0099] ②Forklift power consumption: multiply the forklift power supply voltage and the feedback current vector sum to get the forklift power consumption.

[0100] 4) Forklift utilization rate

[0101] ① Daily/monthly statistics of forklift power-on time and motor working time. The on-line rate and operating rate of forklifts are used as the evaluation indicators of forklift utilization.

[0102] ②Statistical data on the usage rate (day/month) of each forklift every month.

[0103] 5) Abnormal situation of forklift

[0104] ① Classified and statistical data of various fault alarms;

[0105] ②Collision times, running data before and after the collision (including: drive, motor, temperature, acceleration, driver operation records, etc.);

[0106] ③Overload records, including: overload time and overload times;

[0107] ④ Records of abnormal road conditions, including: ultra-safe angle driving and abnormal road bumps.

[0108] 6) The health status of the battery

[0109] ① battery current, voltage and power value;

[0110] ②Analysis and evaluation of battery health status.

[0111] 7) Drive operation

[0112] ①Driver routine data statistics, including: maximum current, maximum voltage, maximum temperature, etc.

[0113] ② Driver control performance evaluation, including: overshoot and response time, etc.

[0114] 8) Motor running condition

[0115] ①Motor general data, including: maximum current, maximum voltage and maximum temperature, etc.

[0116] ② Motor performance evaluation, including: shaft vibration.

[0117] It should be noted that the feature values ​​extracted from the historical operation data in this step are: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, driver operation and motor operation Any or all of the situations, wherein the characteristic values ​​include but are not limited to the listed eight types, and other characteristic values ​​can also be added according to actual needs, depending on actual needs, and the present invention is not limited here.

[0118] Step S103, using each dimension index in the forklift equipment status description information as a feature vector, performing local quantitative scoring on multiple feature vectors based on historical operating data, and generating a high-dimensional feature vector as a forklift overall health evaluation vector;

[0119] Among them, the process of locally quantifying and scoring multiple feature vectors based on historical operating data is a process of scoring feature vectors based on empirical data. For example, if a forklift has been in an overloaded working state, the feature vector The environment can be rated as 50 points; when the forklift is running under good working conditions, the eigenvector forklift working environment can be rated as 90 points. The health status of the battery can be scored in reverse according to its service life, and so on.

[0120] Step S104 , perform percentage-weighted summation on each component of the high-dimensional feature vector to obtain a percentage, and use the percentage as the overall health evaluation value of the forklift to comprehensively evaluate the state of the forklift equipment.

[0121] Wherein, the weight of each component of the high-dimensional feature vector may be determined according to actual needs.

[0122] For example, select five eigenvectors of forklift load, forklift power consumption, forklift utilization rate, forklift abnormality and battery health status to comprehensively evaluate the state of forklift equipment. These five eigenvectors are scored according to the percentage system in step S103, respectively : The load of the forklift is 80 points, the power consumption of the forklift is 90 points, the utilization rate of the forklift is 85 points, the abnormal situation of the forklift is 95 points, and the health status of the battery is 70 points; then the weighted ratio of these five items is set to 3 according to experience: 3:2:1:1, then the percentage weighted summation of the five eigenvectors is performed, and the obtained percentage is: 0.8*0.3+0.9*0.3+0.85*0.3+0.95*0.1+0.7*0.1=0.93, therefore, The overall health evaluation value of the forklift is 0.93.

[0123] In summary, the present invention discloses a method for comprehensive evaluation of the state of forklift equipment, which obtains historical operating data of forklifts, performs preprocessing and feature value extraction on the historical operating data, obtains state description information of forklift equipment, and converts the state description information of forklift equipment to Each dimensional index in the forklift is used as a feature vector, and multiple feature vectors are respectively quantified and scored based on historical operating data to generate a high-dimensional feature vector, which is used as the overall health evaluation vector of the forklift, and the percentages of each component of the high-dimensional feature vector A weighted sum is obtained to obtain a percentage, and the percentage is used as the overall health evaluation value of the forklift to comprehensively evaluate the state of the forklift equipment. When the present invention comprehensively evaluates the state of the forklift equipment, multiple dimensions are considered comprehensively, including: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, and driver operating conditions Therefore, a comprehensive evaluation of the operating status of forklifts can be realized, which not only solves the equipment status description information required for further equipment data analysis such as forklift maintenance, but also helps forklift manufacturing The supplier realizes the analysis of the long-term operation of the forklift, and then maintains and designs the auxiliary equipment to ensure the normal use of the forklift, prolong the service life of the forklift, and ensure the working efficiency of the forklift.

[0124] Corresponding to the foregoing method embodiments, the present invention also discloses a device for comprehensively evaluating the state of forklift equipment.

[0125] see figure 2 , a structural schematic diagram of a device for comprehensive evaluation of forklift equipment status disclosed in an embodiment of the present invention, the device includes:

[0126] An acquisition unit 201, configured to acquire historical operating data of the forklift;

[0127] Among them, the historical operation data of the forklift includes: using the linear regression method to obtain the feedback torque current of the lifting motor, the speed of the lifting motor, the battery voltage, the current of the traveling motor and the speed of the traveling motor required by the forklift load;

[0128] The mechanism model is used to derive and calculate the lift cylinder pressure sensor data, acceleration sensor data, gyroscope sensor data, motor speed, etc. required for the forklift load.

[0129] The processing unit 202 is configured to perform preprocessing and feature value extraction on the historical operation data to obtain forklift equipment state description information;

[0130] The preprocessing of historical operating data mainly refers to: data cleaning of historical operating data, including: deleting irrelevant data and duplicate data in the original data set, smoothing noise data, screening out data irrelevant to the mining topic, and dealing with missing values ​​and abnormalities value etc.

[0131] It should be noted that the method or algorithm of each state description in the forklift equipment state description information can not only be applied to the feature value extraction of the forklift historical operation data, but also can be used for the feature value extraction of the forklift current operation condition.

[0132] Wherein, the forklift device state description information includes multiple dimension indicators, and the multiple dimension indicators include: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, and drive operation condition and any or all of the operating conditions of the motor.

[0133] Eigenvalue extraction is a method to transform the group measurement values ​​of a certain mode to highlight the representative characteristics of the mode.

[0134] In this embodiment, the state of the forklift equipment can be described from eight aspects. In practical applications, these eight aspects can be refined into multiple small eigenvalues. By combining these eigenvalues, the forklift equipment state can be realized. Comprehensive analysis, so that the evaluation of the state of the forklift is more comprehensive and prepared.

[0135] Below, the eight aspects of the description of the state of forklift equipment are introduced in detail, as follows:

[0136] 1) Forklift load

[0137] The load estimation of the forklift can be obtained by using the linear regression method of the historical operation data of the forklift or by deriving and calculating the mechanism model.

[0138] The linear regression method is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship between two or more variables.

[0139] ① The processing unit 202 obtains the load of the forklift by using the linear regression method on the historical operation data of the forklift as follows:

[0140] The forklift load mass M is obtained by using the linear regression method on the historical operation data.

[0141] M=(h 1 , h 2 , h 3 , h 4 , h 5 )(x 1 ,x 2 ,x 3 ,x 4 ,x 5 ) T

[0142] Among them, h 1 Feedback torque current for lifting motor, h 2 is the lifting motor speed, h 3 is the battery voltage, h 4 is the walking motor current, h 5 is the travel motor speed, x 1 ,x 2 ,x 3 ,x 4 ,x 5 is the linear regression model parameter.

[0143] Among them, the parameter x 1 ,x 2 ,x 3 ,x 4 ,x 5 It can be obtained by performing linear regression on the historical operation data of the forklift.

[0144] Specifically, the least square method is used to learn and identify the historical operation data of forklifts input into the linear regression model, and the parameter x 1 ,x 2 ,x 3,x 4 ,x 5 , that is, the load M can be calculated according to the linear regression model.

[0145] It should be noted that parameter identification is a technology that combines theoretical models and experimental data for prediction. A set of parameter values ​​is determined according to experimental data and established models, so that the numerical results obtained by the model can be the best. Fit the test data.

[0146] The parameter identification ground push formula that the present invention adopts when learning identification is as follows:

[0147] K(m+1)=P(m)x(m+1)[1+x T (m+1)P(m)x(m+1)] -1;

[0148] P(m)=(x T (m)x(m)) -1;

[0149] P(m+1)=P(m)-K(m+1)x T (m+1)P(m);

[0150]

[0151] In the formula, x is the input of the forklift system, corresponding to h in the calculation formula of the forklift load mass M 1 ~ h 5 The value of , y is the output of the forklift system, corresponding to the forklift load mass M, m is the number of recursions, is the parameter estimate, K is the gain matrix, K(m+1) is the gain matrix under the m+1th recursion, P(m) is the intermediate process quantity, x(m+1) is the m+1th time System input under recursion, x T (m+1) is the transpose of the system input under the m+1th recursion, x T (m) is the transposition of the system input under the m-th recursion, x(m) is the system input under the m-th recursion, P(m+1) is the intermediate process quantity, is the estimated value of the parameter under the m+1th recursion, is the estimated value of the parameter under the mth recursion, and y(m+1) is the system output under the mth recursion.

[0152] Among them, after the forklift load corresponding to the forklift work data is determined, self-learning can be performed to correct the parameters. The forklift work data includes: h 1 Feedback torque current for lifting motor, h 2 is the lifting motor speed, h 3 is the battery voltage, h 4 is the walking motor current, h 5 is the travel motor speed, and the forklift load is the forklift load mass M.

[0153] ②The processing unit 202 uses the mechanism model to deduce and calculate the forklift load from the historical operation data of the forklift as follows:

[0154] The forklift load calculation model is obtained by combining the historical operation data of the forklift and the operation mechanism of the forklift, and the forklift load is determined based on the load calculation model, specifically: the lifting dynamic model (F=ma) based on the forklift movement and the current based on the motor operation, The walking dynamics model established by the torque and rotational speed is used to obtain the forklift mechanism model; the forklift mechanism model is corrected to obtain the corrected mechanism model, and the forklift load calculation model is obtained based on the corrected mechanism model and historical operation data, and the forklift load is determined according to the forklift load calculation model .

[0155] Among them, the current, torque and rotational speed of the motor can be directly measured by the corresponding sensors. A lift cylinder pressure sensor and an acceleration sensor are installed on the forklift, and the acceleration sensor is used to measure the travel acceleration of the forklift.

[0156] The walking dynamics model is:

[0157] f q -f v v-f·sign(v)·M=Ma

[0158] f q =τR-f τ = kI q -f τ

[0159]

[0160] In the formula, M is the overall load of the vehicle body, a is the travel acceleration of the forklift, F q is the lift cylinder pressure, f v is the viscous friction coefficient of forklift driving, f is the sliding friction coefficient, f τ is the rotational friction coefficient of the motor, τ is the motor torque of the forklift, R is the radius of the forklift wheel, I q is the current, k is the model parameter, v is the running speed of the forklift, and sign(v) is a mathematical function calculation for v, specifically when x>0, sign(x)=1; when x=0, sign(x )=0; when x<0, sign(x)=-1.

[0161] The lift dynamics model is:

[0162] F-mg-f=ma, where the cylinder thrust is F=kI q or F=kP

[0163] The formula for calculating the load mass of the forklift is obtained by identifying the comprehensive friction coefficient f of the parameters and the model parameter k, and the model parameter k is a known quantity.

[0164] Based on the forklift mechanism model and the historical operation data of the forklift, the forklift load calculation model is obtained, and the forklift load calculation model is used to estimate the maximum load and the average load of the forklift in the preset time period, and the maximum load and the average load are used as the forklift in the forklift. Load conditions during the preset time period.

[0165] 2) Forklift working environment

[0166] ① The degree of vibration in the operating environment of the forklift;

[0167] The up and down acceleration measured by the acceleration sensor installed on the forklift is used as a measure of the degree of bumpiness in the operating environment of the forklift.

[0168] ② The slope of the running road;

[0169] The inclination angle measured by the gyroscope installed on the forklift is used as a measure of the slope of the running road.

[0170] ③Forklift running stability;

[0171] The fore-and-aft acceleration measured by the acceleration sensor installed on the forklift is used as a measure of whether the forklift is running smoothly.

[0172] ④Whether the forklift is reversing;

[0173] The motor keeps rotating forward while the forklift is moving forward. If the motor speed has a negative value, it indicates that the forklift driver is reversing during the handling process, which means that the working environment of the forklift is relatively narrow and there are places where it is impossible to turn.

[0174] ⑤The journey of a forklift to carry the goods;

[0175] Based on the lift motor current and the integral value of the motor speed, the distance for the forklift to carry the goods in one trip is determined. Specifically: integrating the travel motor speed between two adjacent lifting motor current peak values ​​to estimate the distance for a forklift to carry a cargo.

[0176] It should be noted that the working environment of the forklift includes but is not limited to the five situations listed above. In practical applications, the working environment of the forklift can be any one or a combination of several of the above five situations. It can also be based on the actual situation. Adding the determination conditions for the working environment of the forklift depends on actual needs, which is not limited in the present invention.

[0177] 3) Forklift power consumption

[0178] ① Electricity used by the forklift;

[0179] ②Forklift power consumption: multiply the forklift power supply voltage and the feedback current vector sum to get the forklift power consumption.

[0180] 4) Forklift utilization rate

[0181] ① Daily/monthly statistics of forklift power-on time and motor working time. The on-line rate and operating rate of forklifts are used as the evaluation indicators of forklift utilization.

[0182] ②Statistical data on the usage rate (day/month) of each forklift every month.

[0183] 5) Abnormal situation of forklift

[0184] ① Classified and statistical data of various fault alarms;

[0185] ②Collision times, running data before and after the collision (including: drive, motor, temperature, acceleration, driver operation records, etc.);

[0186] ③Overload records, including: overload time and overload times;

[0187] ④ Records of abnormal road conditions, including: ultra-safe angle driving and abnormal road bumps.

[0188] 6) The health status of the battery

[0189] ① battery current, voltage and power value;

[0190] ②Analysis and evaluation of battery health status.

[0191] 7) Drive operation

[0192] ①Driver routine data statistics, including: maximum current, maximum voltage, maximum temperature, etc.

[0193] ② Driver control performance evaluation, including: overshoot and response time, etc.

[0194] 8) Motor running condition

[0195] ①Motor general data, including: current maximum value, voltage maximum value and maximum temperature, etc.

[0196] ② Motor performance evaluation, including: shaft vibration.

[0197] It should be noted that the characteristic values ​​extracted from the historical operation data in this embodiment are: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, driver operation condition and motor Any or all of the operating conditions, wherein the eigenvalues ​​include but are not limited to the eight listed, and other eigenvalues ​​can also be added according to actual needs, depending on actual needs, and the present invention is not limited here .

[0198] The high-dimensional feature vector generation unit 203 is configured to use each dimensional index in the forklift equipment status description information as a feature vector, perform local quantification and scoring on a plurality of the feature vectors based on the historical operation data, and generate a high-dimensional feature vector. The dimension feature vector is used as the overall health evaluation vector of the forklift;

[0199] Among them, the process of local quantitative scoring of multiple feature vectors based on historical operating data is a process of scoring feature vectors based on empirical data. For example, if a forklift has been in an overloaded working state, the feature vector forklift work The environment can be rated as 50 points; when the forklift is running under good working conditions, the feature vector forklift working environment can be rated as 90 points. The health status of the battery can be scored in reverse according to its service life, and so on.

[0200] The state evaluation unit 204 is configured to perform percentage-weighted summation on each component of the high-dimensional feature vector to obtain a percentage, and use the percentage as the overall health evaluation value of the forklift to comprehensively evaluate the state of the forklift equipment.

[0201] Wherein, the weight of each component of the high-dimensional feature vector may be determined according to actual needs.

[0202]For example, select five eigenvectors of forklift load, forklift power consumption, forklift utilization rate, forklift abnormality and battery health status to comprehensively evaluate the state of forklift equipment. These five eigenvectors are scored according to the percentage system in step S103, respectively : The load of the forklift is 80 points, the power consumption of the forklift is 90 points, the utilization rate of the forklift is 85 points, the abnormal situation of the forklift is 95 points, and the health status of the battery is 70 points; then the weighted ratio of these five items is set to 3 according to experience: 3:2:1:1, then the percentage weighted summation of the five eigenvectors is performed, and the obtained percentage is: 0.8*0.3+0.9*0.3+0.85*0.3+0.95*0.1+0.7*0.1=0.93, therefore, The overall health evaluation value of the forklift is 0.93.

[0203] In summary, the present invention discloses a device for comprehensive evaluation of the state of forklift equipment, which acquires historical operating data of forklifts, performs preprocessing and feature value extraction on the historical operating data, obtains state description information of forklift equipment, and converts the state description information of forklift equipment to Each dimensional index in the forklift is used as a feature vector, and multiple feature vectors are respectively quantified and scored based on historical operating data to generate a high-dimensional feature vector, which is used as the overall health evaluation vector of the forklift, and the percentages of each component of the high-dimensional feature vector A weighted sum is obtained to obtain a percentage, and the percentage is used as the overall health evaluation value of the forklift to comprehensively evaluate the state of the forklift equipment. When the present invention comprehensively evaluates the state of the forklift equipment, multiple dimensions are considered comprehensively, including: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, and driver operating conditions Therefore, a comprehensive evaluation of the operating status of forklifts can be realized, which not only solves the equipment status description information required for further equipment data analysis such as forklift maintenance, but also helps forklift manufacturing The supplier realizes the analysis of the long-term operation of the forklift, and then maintains and designs the auxiliary equipment to ensure the normal use of the forklift, prolong the service life of the forklift, and ensure the working efficiency of the forklift.

[0204] Corresponding to the above-mentioned system embodiment, the present invention also discloses a forklift equipment status evaluation system.

[0205] see image 3 , a schematic structural diagram of a forklift equipment status evaluation system disclosed in an embodiment of the present invention, the system includes: a forklift operation data collection device 301, a cloud server 302 and a local server 303, wherein the local server 303 includes figure 2 In the device for evaluating the state of forklift equipment in the illustrated embodiment, the cloud server 302 is connected to the forklift operation data collection device 301 and the local server 303 respectively;

[0206] in,

[0207] The forklift operation data collection device 301 is used to be installed on the forklift, collect the operation data of the forklift, and upload the operation data of the forklift to the cloud server 302. In practical applications, the forklift operation data collection device 301 can collect the collected forklift operation data The data is transmitted to the cloud server 302 through a wireless network such as WiFi/4G.

[0208] The forklift operation data acquisition device 301 includes, but is not limited to, a lift cylinder pressure sensor and an acceleration sensor.

[0209] The cloud server 302 is used to store the historical operation data of the forklift, and can receive the data acquisition instruction sent by the local server 303 , and send the historical operation data of the forklift to the local server 303 .

[0210] The local server 303 can store the obtained historical operation data of the forklift in the HDFS distributed file system, and use the MapReduce computing framework to perform statistical analysis on the historical operation data of the forklift to obtain the status description information of the forklift.

[0211] It should be noted that, the process for the local server 303 to comprehensively evaluate the state of the forklift equipment using the acquired historical operation data of the forklift can refer to the corresponding embodiments above, and will not be repeated here.

[0212] In summary, the comprehensive evaluation system for forklift equipment status disclosed in the present invention includes: forklift operation data collection device 301, cloud server 302 and local server 303, forklift operation data collection device 301 collects forklift operation data, and uploads it to the cloud The server 302 and the local server 303 obtain the historical operation data of the forklift from the cloud server 302, carry out preprocessing and feature value extraction through the historical operation data, obtain the forklift equipment status description information, and use each dimension index in the forklift equipment status description information as A feature vector, based on historical operating data, perform local quantification and scoring on multiple feature vectors to generate high-dimensional feature vectors, which are used as the overall health evaluation vector of forklifts. Percentage-weighted summation is performed on each component of the high-dimensional feature vector to obtain a percentage , use the percentage as the overall health evaluation value of the forklift to comprehensively evaluate the equipment status of the forklift. When the present invention comprehensively evaluates the state of the forklift equipment, multiple dimensions are considered comprehensively, including: forklift load, forklift working environment, forklift power consumption, forklift utilization rate, forklift abnormality, battery health status, and driver operating conditions Therefore, a comprehensive evaluation of the operating status of forklifts can be realized, which not only solves the equipment status description information required for further equipment data analysis such as forklift maintenance, but also helps forklift manufacturing The supplier realizes the analysis of the long-term operation of the forklift, and then maintains and designs the auxiliary equipment to ensure the normal use of the forklift, prolong the service life of the forklift, and ensure the working efficiency of the forklift.

[0213] Finally, it should also be noted that in this text, relational terms such as first and second etc. are only used to distinguish one entity or operation from another, and do not necessarily require or imply that these entities or operations, any such actual relationship or order exists. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

[0214] Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other.

[0215] The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.