CN105243253B - A kind of climbing frame condition detection method and device - Google Patents
A kind of climbing frame condition detection method and device Download PDFInfo
- Publication number
- CN105243253B CN105243253B CN201410733786.8A CN201410733786A CN105243253B CN 105243253 B CN105243253 B CN 105243253B CN 201410733786 A CN201410733786 A CN 201410733786A CN 105243253 B CN105243253 B CN 105243253B
- Authority
- CN
- China
- Prior art keywords
- climbing frame
- pin
- inclination angle
- resistance
- chip
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a kind of climbing frame condition detection method and device, by building neural network model, neural network model includes input layer, hidden layer and output layer, the inclination angle before and after climbing frame is obtained, left and right inclination angle, four parameters of gravity and the rate of climb, by the front and rear inclination angle of climbing frame, left and right inclination angle, four parameters of gravity and the rate of climb are input in input layer after being normalized as the input data of neural network model, the input layer of neutral net, hidden layer and output layer handle data progress the output for obtaining neural network model according to the transfer function of setting successively, the output of the neural network model is the corresponding exponential quantity of climbing frame state, it is the state that can determine that climbing frame according to the corresponding exponential quantity of climbing frame state；Advantage is that the exponential quantity considers the abnormal speed of service, payload overload or loses the unsafe condition such as load and climbing frame inclination comprehensively, and accuracy of detection is higher, the state of climbing frame is accurately held comprehensively, it is ensured that the safe operation of climbing frame.
Description
Technical field
The present invention relates to a kind of climbing frame state inspection, more particularly, to a kind of climbing frame condition detection method and device.
Background technology
With the fast development of China's economy, skyscraper is more and more.During high-building construction, climbing frame is played
More and more important effect.Climbing frame in the process of running, it is possible that the speed of service is abnormal, payload overload or lose is carried and climbing frame
The unsafe conditions such as inclination.When these unsafe conditions occur, if dangerous situation may be occurred by not being subject to alarm, wealth is gently then caused
Production loss, life security that is heavy then jeopardizing people.Therefore, how effectively climbing frame state to be detected and assessed to safety in production
It is significant.
Existing climbing frame condition detection method is mainly included the following steps that：The normal loading model of climbing frame is set in the controller
Enclose, then detect and obtain the current load of climbing frame, current load is contrasted with normal loading scope, if current load
Do not fall within the range of normal loading, then show climbing frame overload or lose to carry.Existing climbing frame condition detection method is only capable of detecting climbing frame
Load state is lost in overload, but during climbing frame operation, actual conditions are sufficiently complex, and the inclination of climbing frame main body or climbing speed are abnormal
Dangerous situation is all likely to occur, existing climbing frame condition detection method can not detect acquisition climbing frame speed of service abnormality and tilt and endanger
Dangerous state, it is impossible to accurately hold the state of climbing frame comprehensively.
The content of the invention
One of technical problems to be solved by the invention are to provide a kind of climbing frame condition detection method, the climbing frame state-detection
Method obtains the front and rear inclination angle, left and right inclination angle, four ginsengs of gravity and the rate of climb of climbing frame by building neural network model
Number, nerve net is used as after the front and rear inclination angle of climbing frame, left and right inclination angle, four parameters of gravity and the rate of climb are normalized
The input data of network model, calculates from there through neural network model and obtains the corresponding exponential quantity of climbing frame state, according to the index
Value judges the state of climbing frame, and the exponential quantity considers the danger such as the abnormal speed of service, payload overload or mistake are carried and climbing frame is tilted comprehensively
Dangerous situation, accuracy of detection is higher, the state of climbing frame is accurately held comprehensively, it is ensured that the safe operation of climbing frame.
The present invention solve technical scheme that one of above-mentioned technical problem used for：A kind of climbing frame condition detection method, bag
Include following steps：
1. neural network model is built, described neural network model includes input layer, hidden layer and output layer；
Described input layer is used for input data, and the input vector of described input layer is Xi=[xi1 xi2 xi3 xi4],
Wherein, xi1Represent the front and rear inclination angle detection data of climbing frame, xi2Represent the left and right inclination angle detection data of climbing frame, xi3Represent climbing frame
Gravity detects data, xi4Represent the rate of climb detection data of climbing frame；
Described hidden layer includes ten neuron nodes, and described hidden layer is used for the input for receiving described input layer
Data, the transfer function of the neuron node of described hidden layer is f1(x), f1(x) it is tansig functions,E is the truth of a matter of natural logrithm, e=2.718281828459；
The output of described hidden layerW1For the weight matrix of hidden layer, subscript T representing matrixs
Transposition, b1For the threshold matrix of hidden layer, W1And b1It is expressed as respectively with the form of matrix：
Described output layer receives described hidden layer output, and described output layer includes a neuron node, described
Output layer neuron node transfer function be f2(x), f2(x) it is purelin functions, f2(x)=x；Described output layer
Output o2=f2(W2o1+b2)=f2(W2f1(W1Xi T+b1)+b2), wherein W2For the weight matrix of output layer, b2For output layer
Threshold matrix, W2And b2It is expressed as respectively with the form of matrix：
W2=[- 0.2282 1.1340-0.6504-0.1181-0.0120 0.2103 0.8087-0.5868
0.0913 -0.5395]
b2=[0.6769]；
The output y=o of described neural network model2；
2. the front and rear inclination angle, left and right inclination angle, four parameters of gravity and the rate of climb of climbing frame are gathered and obtained in real time；
3. transfer function is passed throughThe front and rear inclination angle of the climbing frame 2. obtained to step respectively, left and right inclination angle,
Four parameters of gravity and the rate of climb are normalized, and respectively obtain the front and rear inclination angle normalization data of climbing frame, climbing frame
The rate of climb normalization data of left and right inclination angle normalization data, the gravity normalization data of climbing frame and climbing frame, wherein x*Respectively
Inclination angle, left and right inclination angle, the normalization data of four parameters of gravity and the rate of climb before and after correspondence；X corresponds to step and 2. obtained respectively
The front and rear inclination angle of climbing frame, left and right inclination angle, four parameters of gravity and the rate of climb, max corresponds to the front and rear inclination angle of climbing frame, climbs respectively
The maximum that four parameters of the rate of climb at the left and right inclination angle of frame, the gravity of climbing frame and climbing frame can reach, min corresponds to climbing frame respectively
Front and rear inclination angle, the minimum value that can reach of the left and right inclination angle of climbing frame, four parameters of the rate of climb of the gravity of climbing frame and climbing frame；
4. using the front and rear inclination angle normalization data of climbing frame as climbing frame front and rear inclination angle detection data xi1, the lateral tilting of climbing frame
Angle normalization data as climbing frame left and right inclination angle detection data xi2, the gravity normalization data of climbing frame examines as the gravity of climbing frame
Survey data xi3With the rate of climb normalization data of climbing frame data x is detected as the rate of climb of climbing framei4It is input to neutral net
In the input layer of model, the output y for obtaining neural network model is calculated；
5. the output y of neural network model is made decisions, decision function is as follows：
If y value is less than 0.60, climbing frame state is safety；If y value is more than or equal to 0.60 and is less than
When 0.85, climbing frame state is warning；If y value is more than or equal to 0.85 and is less than or equal to 1, climbing frame state is danger.
Compared with prior art, the advantage of method of the invention is by building neural network model, neutral net mould
Type includes input layer, hidden layer and output layer, obtains the front and rear inclination angle, left and right inclination angle, four ginsengs of gravity and the rate of climb of climbing frame
Number, nerve net is used as after the front and rear inclination angle of climbing frame, left and right inclination angle, four parameters of gravity and the rate of climb are normalized
The input data of network model is input in input layer, input layer, hidden layer and the output layer of neutral net according to setting transmission
Function handles data progress the output for obtaining neural network model successively, and the output of the neural network model is climbing frame state
Corresponding exponential quantity, is the state that can determine that climbing frame according to the corresponding exponential quantity of climbing frame state, and the exponential quantity considers fortune comprehensively
Row velocity anomaly, payload overload lose the unsafe condition such as load and climbing frame inclination, and accuracy of detection is higher, and climbing frame is accurately held comprehensively
State, it is ensured that the safe operation of climbing frame.
The two of the technical problems to be solved by the invention are to provide a kind of climbing frame condition checkout gear, the climbing frame state-detection
Neural network model is provided with the central processing unit of device, the first Acquisition Circuit gathers the front and rear inclination angle and left and right of climbing frame in real time
Inclination angle simultaneously sends central processing unit to, and the second Acquisition Circuit gathers the gravity of climbing frame and sends central processing unit in real time, and the 3rd
Acquisition Circuit gathers the position of climbing frame and sends central processing unit in real time, and central processing unit is by front and rear inclination angle, the left and right of climbing frame
Inclination angle, four parameters of gravity and the rate of climb be normalized after as neural network model input data, nerve net
Network model, which is calculated, obtains the corresponding exponential quantity of climbing frame state, and central processing unit judges the state of climbing frame according to the exponential quantity, and this refers to
Numerical value considers the abnormal speed of service, payload overload or loses the unsafe conditions such as load, electrical fault and climbing frame inclination, detection essence comprehensively
Degree is higher, the state of climbing frame is accurately held comprehensively, it is ensured that the safe operation of climbing frame.
The present invention solve above-mentioned technical problem two technical schemes used for：A kind of climbing frame condition checkout gear, bag
Central processing unit, the first Acquisition Circuit for gathering inclination angle and left and right inclination angle before and after climbing frame are included, for gathering climbing frame gravity
Second Acquisition Circuit, the 3rd Acquisition Circuit, green indicating lamp, relay and alarm for gathering climbing frame position, it is described
Central processing unit respectively with the first described Acquisition Circuit, the second described Acquisition Circuit, the 3rd described Acquisition Circuit, described
Green indicating lamp, described relay and the connection of described alarm, be provided with neutral net in described central processing unit
Model, described neural network model includes input layer, hidden layer and output layer；
Described input layer is used for input data, and the input vector of described input layer is Xi=[xi1 xi2 xi3 xi4],
Wherein, xi1Represent the front and rear inclination angle detection data of climbing frame, xi2Represent the left and right inclination angle detection data of climbing frame, xi3Represent climbing frame
Gravity detects data, xi4Represent the rate of climb detection data of climbing frame；
Described hidden layer includes ten neuron nodes, and described hidden layer is used for the input for receiving described input layer
Data, the transfer function of the neuron node of described hidden layer is f1(x), f1(x) it is tansig functions,E is the truth of a matter of natural logrithm, e=2.718281828459；
The output of described hidden layerW1For the weight matrix of hidden layer, subscript T representing matrixs
Transposition, b1For the threshold matrix of hidden layer, W1And b1It is expressed as respectively with the form of matrix：
Described output layer receives described hidden layer output, and described output layer includes a neuron node, described
Output layer neuron node transfer function be f2(x), f2(x) it is purelin functions, f2(x)=x；Described output layer
OutputW2For the weight matrix of output layer, b2For output layer
Threshold matrix, W2And b2It is expressed as respectively with the form of matrix：
W2=[- 0.2282 1.1340-0.6504-0.1181-0.0120 0.2103 0.8087-0.5868
0.0913 -0.5395]
b2=[0.6769]；
The output y=o of described neural network model2；
The first described Acquisition Circuit gathers the front and rear inclination angle and left and right inclination angle of climbing frame and sends described center in real time
Processor, the second described Acquisition Circuit gathers the gravity of climbing frame and sends described central processing unit in real time, and described the
Three Acquisition Circuits gather the position of climbing frame and send described central processing unit in real time, and described central processing unit will be described
The change in location of climbing frame is converted to the rate of climb of climbing frame, and described central processing unit is respectively by front and rear inclination angle, the left and right of climbing frame
Inclination angle, four parameters of gravity and the rate of climb use transfer functionIt is normalized, respectively obtains and climb
The front and rear inclination angle normalization data of frame, the left and right inclination angle normalization data of climbing frame, the gravity normalization data of climbing frame and climbing frame
Rate of climb normalization data, wherein x*Returning for front and rear inclination angle, left and right inclination angle, gravity and four parameters of the rate of climb is corresponded to respectively
One changes data；X corresponds to the front and rear inclination angle, left and right inclination angle, four parameters of gravity and the rate of climb of climbing frame respectively, and max is corresponded to respectively
The maximum that the front and rear inclination angle of climbing frame, the left and right inclination angle of climbing frame, four parameters of the rate of climb of the gravity of climbing frame and climbing frame can reach
Value, min corresponds to four ginsengs of the rate of climb of front and rear inclination angle, the left and right inclination angle of climbing frame, the gravity of climbing frame and the climbing frame of climbing frame respectively
The minimum value that number can reach；Using the front and rear inclination angle normalization data of climbing frame as climbing frame front and rear inclination angle detection data xi1, climbing frame
Left and right inclination angle normalization data as climbing frame left and right inclination angle detection data xi2, the gravity normalization data of climbing frame is used as climbing frame
Gravity detection data xi3With the rate of climb normalization data of climbing frame data x is detected as the rate of climb of climbing framei4It is input to
In the input layer of neural network model, the output y for obtaining neural network model is calculated, if y value is less than 0.60, climbing frame
State is safety, and the described green indicating lamp of described central processing unit driving lights；If y value be more than or equal to 0.60 and
During less than 0.85, climbing frame state is warning, and the described alarm of described central processing unit driving sends alarm；If y's takes
When value is more than or equal to 0.85 and is less than or equal to 1, climbing frame state is danger, and the alarm described in described central processing unit driving is sent out
Driving described relay to disconnect while going out alarm makes climbing frame stop motion.
Described central processing unit includes model STM32F103RBT6 the first chip, the second of model ULN2003
Chip, serial port connector, first resistor, second resistance, 3rd resistor, the 4th resistance, the first electric capacity, the second electric capacity, the 3rd electricity
Hold, crystal oscillator and switch, the PC1 pin of the first described chip are connected with the output end of the 3rd described Acquisition Circuit, described the
The output end connection of the PC2 pin of one chip and the second described Acquisition Circuit, the PA9 pin and PA10 pin of described the first chip is logical
Serial port connector is crossed to be connected with the first described Acquisition Circuit, the PA3 pin of described the first chip and the second described chip
IN1 pin are connected by described first resistor, and the IN3 pin of the PA2 pin of described the first chip and the second described chip pass through
The IN5 pin of described second resistance connection, the PA1 pin of described the first chip and the second described chip pass through the described the 3rd
Resistance is connected, VDD pin, one end connection of VDDA pin and the 4th described resistance and the access 3.3V electricity of described the first chip
Pressure, the other end of described the 4th resistance, the NRST pin of the first described chip, one end of the first described electric capacity and described
One end connection of switch, the other end of described switch, the other end of the first described electric capacity, the first described chip
B00T0 pin, BOOT1 pin, VSS pin and VSSA pin are grounded, the OSCIN pin of described the first chip, described the second electric capacity
One end and the connection of one end of described crystal oscillator, the OSCOUT pin of described the first chip, one end of the 3rd described electric capacity and institute
The other end of the other end connection for the crystal oscillator stated, the other end of described the second electric capacity and the 3rd described electric capacity is grounded, institute
The COM pin access 24V voltages for the second chip stated.Structure tool starts the advantages of stabilization, hand-reset and strong driving force.
The first described Acquisition Circuit includes obliquity sensor, and described obliquity sensor is arranged on climbing frame.
The second described Acquisition Circuit includes the gravity sensor and the first signal conditioning circuit being arranged on climbing frame, described
The first signal conditioning circuit include the 5th resistance, the 6th resistance, the 4th electric capacity, the first diode and the second diode, it is described
Gravity sensor, one end connection of one end of described 5th resistance and the 6th described resistance, described the 5th resistance
The other end, one end of the 4th described electric capacity, the anode of the negative electrode of the first described diode and the second described diode connect
Connect and its connection end be the second described Acquisition Circuit output end, the other end of described the 6th resistance, the 4th described electricity
The anode of the other end of appearance and the first described diode is grounded, and the negative electrode of the second described diode accesses 3.3V voltages.
The structure has the advantages that simple in construction, reliable and stable, data processing precision is high.
The 3rd described Acquisition Circuit includes the position sensor and secondary signal modulate circuit being arranged on climbing frame, described
Secondary signal modulate circuit include the 7th resistance, the 8th resistance, the 5th electric capacity, the 3rd diode and the 4th diode, it is described
Position sensor, one end connection of one end of described 7th resistance and the 8th described resistance, described the 7th resistance
The other end, one end of the 5th described electric capacity, the anode of the negative electrode of the 3rd described diode and the 4th described diode connect
Connect and its connection end be the 3rd described Acquisition Circuit output end, the other end of described the 8th resistance, the 5th described electricity
The anode of the other end of appearance and the 3rd described diode is grounded, and the negative electrode of the 4th described diode accesses 3.3V voltages.
The structure has the advantages that simple in construction, reliable and stable, data processing precision is high.
Described central processing unit is also associated with storage circuit, and described storage circuit includes the of model AT24C64
Three chips, the 9th resistance and the tenth resistance, A0 pin, A1 pin, A2 pin, GND pin and the WP pin of the 3rd described chip are grounded, institute
One end connection of the VCC pin for the 3rd chip stated, one end of the 9th described resistance and the tenth described resistance and access 3.3V
Voltage, the PB6 pin connection of the other end of described the 9th resistance, the SCL pin of the 3rd described chip and the first described chip,
The PB7 pin connection of the other end of the tenth described resistance, the SDA pin of the 3rd described chip and the first described chip.
Described central processing unit is also associated with the data transmission circuit for being communicated with external data receiver, institute
The data transmission circuit stated includes model SN65HVD230 CAN transceiver, the 11st resistance and the 12nd resistance, described
The PA12 pin connection of the D pin of CAN transceiver and the first described chip, the R pin and the first described core of described CAN transceiver
The PA11 pin connection of piece, the VCC pin access 3.3V voltages of described CAN transceiver, the GND pin and RS of described CAN transceiver
Pin is grounded, one end connection of the CANH pin of described CAN transceiver and the 11st described resistance, described CAN transceiver
CANL pin and described the 12nd resistance one end connection, the other end and the 12nd described electricity of described the 11st resistance
The other end of resistance is the output end of described CAN transceiver.The structure has the advantages that strong antijamming capability, long transmission distance.
Described central processing unit is also associated with display screen, and described display screen is used to show in described central processing unit
Data, described display screen is the LCD display of dot matrix, the PB8 pin of described the first chip, PB9 pin, PB10 pin,
PB11 pin, PB12 pin, PB13 pin, PB14 pin, PB15 pin, PC0 pin, PC3 pin, PC4 pin, PC5 pin, PC6 pin, PC7 pin and PC8 pin
It is connected with described display screen.The structure has contrast adjustable, the advantages of display content is clear.
Compared with prior art, the advantage of device of the invention is by setting neutral net mould in central processing unit
Type, neural network model include input layer, hidden layer and output layer, the first Acquisition Circuit gather in real time climbing frame front and rear inclination angle and
Left and right inclination angle simultaneously sends central processing unit to, and the second Acquisition Circuit gathers the gravity of climbing frame and sends central processing unit in real time,
3rd Acquisition Circuit gathers the position of climbing frame and sends central processing unit in real time, central processing unit by the front and rear inclination angle of climbing frame,
Left and right inclination angle, four parameters of gravity and the rate of climb are inputted after being normalized as the input data of neural network model
Into input layer, input layer, hidden layer and the output layer of neutral net according to setting transfer function successively to data at
Reason obtains the output of neural network model, and the output of the neural network model is the corresponding exponential quantity of climbing frame state, according to climbing
The corresponding exponential quantity of rack-like state is the state that can determine that climbing frame, and the exponential quantity considers speed of service exception, payload overload comprehensively
Or the unsafe condition such as load and climbing frame inclination is lost, accuracy of detection is higher, the state of climbing frame is accurately held comprehensively, it is ensured that the safety of climbing frame
Running.
Brief description of the drawings
Fig. 1 is the structure chart of the neural network model of the present invention；
Fig. 2 is the theory diagram of the climbing frame condition checkout gear of the present invention；
Fig. 3 is the circuit of the climbing frame condition checkout gear of the present invention；
Fig. 4 is the workflow diagram of the climbing frame condition checkout gear of the present invention.
Embodiment
The climbing frame condition detection method of the present invention is described in further detail below in conjunction with accompanying drawing embodiment.
Embodiment one：As shown in figure 1, a kind of climbing frame condition detection method, comprises the following steps：
1. neural network model is built, neural network model includes input layer, hidden layer and output layer；
Input layer is used for input data, and the input vector of input layer is Xi=[xi1 xi2 xi3 xi4], wherein, xi1Expression is climbed
The front and rear inclination angle detection data of frame, xi2Represent the left and right inclination angle detection data of climbing frame, xi3The gravity detection data of climbing frame are represented,
xi4Represent the rate of climb detection data of climbing frame；
Hidden layer includes ten neuron nodes, and hidden layer is used for the input data for receiving input layer, the nerve of hidden layer
The transfer function of first node is f1(x), f1(x) it is tansig functions,E is the truth of a matter of natural logrithm, e=
2.718281828459；The output of hidden layerWherein W1For the weight matrix of hidden layer, subscript T is represented
The transposition of matrix, b1For the threshold matrix of hidden layer, W1And b1It is expressed as respectively with the form of matrix：
Output layer receives hidden layer output, and output layer includes a neuron node, the biography of the neuron node of output layer
Defeated function is f2(x), f2(x) it is purelin functions, f2(x)=x；The output o of output layer2=f2(W2o1+b2)=f2(W2f1
(W1Xi T+b1)+b2), W2For the weight matrix of output layer, the transposition of subscript T representing matrixs, b2For the threshold matrix of output layer, W2
And b2It is expressed as respectively with the form of matrix：
W2=[- 0.2282 1.1340-0.6504-0.1181-0.0120 0.2103 0.8087-0.5868
0.0913 -0.5395]
b2=[0.6769]；
The output y=o of neural network model2；
2. the front and rear inclination angle, left and right inclination angle, four parameters of gravity and the rate of climb of climbing frame are gathered and obtained in real time；
3. transfer function is passed throughThe front and rear inclination angle of the climbing frame 2. obtained to step respectively, left and right inclination angle,
Four parameters of gravity and the rate of climb are normalized, and respectively obtain the front and rear inclination angle normalization data of climbing frame, climbing frame
The rate of climb normalization data of left and right inclination angle normalization data, the gravity normalization data of climbing frame and climbing frame, wherein x*Respectively
Inclination angle, left and right inclination angle, the normalization data of four parameters of gravity and the rate of climb before and after correspondence；X corresponds to step and 2. obtained respectively
The front and rear inclination angle of climbing frame, left and right inclination angle, four parameters of gravity and the rate of climb, max corresponds to the front and rear inclination angle of climbing frame, climbs respectively
The maximum that four parameters of the rate of climb at the left and right inclination angle of frame, the gravity of climbing frame and climbing frame can reach, min corresponds to climbing frame respectively
Front and rear inclination angle, the minimum value that can reach of the left and right inclination angle of climbing frame, four parameters of the rate of climb of the gravity of climbing frame and climbing frame；
Max and min is determined by the specifications and models of climbing frame；The climbing frame of every kind of specifications and models all clear stipulaties front and rear inclination angle of climbing frame, climb
The left and right inclination angle of frame, the rate of climb of the gravity of climbing frame and climbing frame corresponding max and min；
4. using the front and rear inclination angle normalization data of climbing frame as climbing frame front and rear inclination angle detection data xi1, the lateral tilting of climbing frame
Angle normalization data as climbing frame left and right inclination angle detection data xi2, the gravity normalization data of climbing frame examines as the gravity of climbing frame
Survey data xi3With the rate of climb normalization data of climbing frame data x is detected as the rate of climb of climbing framei4It is input to neutral net
In the input layer of model, the output y for obtaining neural network model is calculated；
5. the output y of neural network model is made decisions, decision function is as follows：
If y value is less than 0.60, climbing frame state is safety；If y value is more than or equal to 0.60 and is less than
When 0.85, climbing frame state is warning；If y value is more than or equal to 0.85 and is less than or equal to 1, climbing frame state is danger.
Present invention also offers a kind of climbing frame condition checkout gear, below in conjunction with climbing frame shape of the accompanying drawing embodiment to the present invention
State detection method is described in further detail.
Embodiment one：As depicted in figs. 1 and 2, a kind of climbing frame condition checkout gear, including central processing unit, for gathering
First Acquisition Circuit at inclination angle and left and right inclination angle before and after climbing frame, for gathering the second Acquisition Circuit of climbing frame gravity, for gathering
The 3rd Acquisition Circuit, green indicating lamp, relay and the alarm of climbing frame position, central processing unit are electric with the first collection respectively
It is provided with road, the second Acquisition Circuit, the 3rd Acquisition Circuit, green indicating lamp, relay and alarm connection, central processing unit
Neural network model, neural network model includes input layer, hidden layer and output layer；
Input layer is used for input data, and the input vector of input layer is Xi=[xi1 xi2 xi3 xi4], wherein, xi1Expression is climbed
The front and rear inclination angle detection data of frame, xi2Represent the left and right inclination angle detection data of climbing frame, xi3The gravity detection data of climbing frame are represented,
xi4Represent the rate of climb detection data of climbing frame；
Hidden layer includes ten neuron nodes, and hidden layer is used for the input data for receiving input layer, the nerve of hidden layer
The transfer function of first node is f1(x), f1(x) it is tansig functions,E is the truth of a matter of natural logrithm, e=
2.718281828459；The output of hidden layerW1For the weight matrix of hidden layer, subscript T representing matrixs
Transposition, b1For the threshold matrix of hidden layer, W1And b1It is expressed as respectively with the form of matrix：
Output layer receives hidden layer output, and output layer includes a neuron node, the biography of the neuron node of output layer
Defeated function is f2(x), f2(x) it is purelin functions, f2(x)=x；The output o of output layer2=f2(W2o1+b2)=f2(W2f1
(W1Xi T+b1)+b2), W2For the weight matrix of output layer, b2For the threshold matrix of output layer, W2And b2The form of matrix is used respectively
It is expressed as：
W2=[- 0.2282 1.1340-0.6504-0.1181-0.0120 0.2103 0.8087-0.5868
0.0913 -0.5395]
b2=[0.6769]；
The output y=o of neural network model2；
First Acquisition Circuit gathers the front and rear inclination angle and left and right inclination angle of climbing frame and sends central processing unit in real time, and second adopts
Collector gathers the gravity of climbing frame and sends central processing unit in real time, and the 3rd Acquisition Circuit gathers position and the biography of climbing frame in real time
Central processing unit is given, central processing unit is converted to the change in location of climbing frame the rate of climb of climbing frame, central processing unit difference
The front and rear inclination angle of climbing frame, left and right inclination angle, four parameters of gravity and the rate of climb are used into transfer functionCarry out
Normalized, respectively obtains front and rear inclination angle normalization data, left and right inclination angle normalization data, the weight of climbing frame of climbing frame of climbing frame
The rate of climb normalization data of power normalization data and climbing frame, wherein x*Respectively correspond to before and after inclination angle, left and right inclination angle, gravity and
The normalization data of four parameters of the rate of climb；X corresponds to front and rear inclination angle, left and right inclination angle, gravity and the rate of climb of climbing frame respectively
Four parameters, max corresponds to the rate of climb of front and rear inclination angle, the left and right inclination angle of climbing frame, the gravity of climbing frame and the climbing frame of climbing frame respectively
The maximum that four parameters can reach, min correspond to respectively the front and rear inclination angle of climbing frame, the left and right inclination angle of climbing frame, the gravity of climbing frame and
The minimum value that four parameters of the rate of climb of climbing frame can reach；Using the front and rear inclination angle normalization data of climbing frame as before and after climbing frame
Inclination angle detection data xi1, the left and right inclination angle normalization data of climbing frame as climbing frame left and right inclination angle detection data xi2, the weight of climbing frame
Power normalization data detects data x as the gravity of climbing framei3With the rising of the rate of climb normalization data of climbing frame as climbing frame
Velocity measuring data xi4It is input in the input layer of neural network model, the output y for obtaining neural network model is calculated, if y
Value be less than 0.60 when, climbing frame state for safety, central processing unit driving green indicating lamp light；If y value is more than
Equal to 0.60 and less than 0.85 when, climbing frame state for warning, central processing unit driving alarm send alarm；If y value
During more than or equal to 0.85 and less than or equal to 1, climbing frame state is danger, and central processing unit driving alarm is driven while send alarm
Motor type relay, which disconnects, makes climbing frame stop motion.
In the present embodiment, as shown in figure 3, central processing unit includes model STM32F103RBT6 the first chip U1, type
Number for ULN2003 the second chip U2, serial port connector P1, first resistor R1, second resistance R2,3rd resistor R3, the 4th electricity
Hinder R4, the first electric capacity C1, the second electric capacity C2, the 3rd electric capacity C3, crystal oscillator J1 and switch S1, the first chip U1 PC1 pin and the 3rd
The output end connection of Acquisition Circuit, the first chip U1 PC2 pin and the output end connection of the second Acquisition Circuit, the first chip U1's
PA9 pin and PA10 pin are connected by serial port connector P1 with the first Acquisition Circuit, the first chip U1 PA3 pin and the second chip U2
IN1 pin connected by first resistor R1, the first chip U1 PA2 pin and the second chip U2 IN3 pin pass through second resistance R2
Connection, the first chip U1 PA1 pin and the second chip U2 IN5 pin are connected by 3rd resistor R3, the first chip U1 VDD
One end connection of pin, VDDA pin and the 4th resistance R4 and access 3.3V voltages, the 4th resistance R4 other end, the first chip U1
NRST pin, the first electric capacity C1 one end and one end connection for switching S1, switch the S1 other end, the first electric capacity C1 other end,
First chip U1 B00T0 pin, BOOT1 pin, VSS pin and VSSA pin is grounded, the first chip U1 OSCIN pin, the second electric capacity
C2 one end and the connection of crystal oscillator J1 one end, the first chip U1 OSCOUT pin, the 3rd electric capacity C3 one end and crystal oscillator J1 it is another
One end is connected, and the second electric capacity C2 other end and the 3rd electric capacity C3 other end are grounded, the second chip U2 COM pin access
24V voltages.
In the present embodiment, as shown in figure 3, the first Acquisition Circuit includes obliquity sensor, obliquity sensor is arranged on climbing frame
On.
In the present embodiment, as shown in figure 3, the second Acquisition Circuit includes the gravity sensor being arranged on climbing frame and the first letter
Number modulate circuit, the first signal conditioning circuit include the 5th resistance R5, the 6th resistance R6, the 4th electric capacity C4, the first diode and
Second diode, one end connection of gravity sensor, the 5th resistance R5 one end and the 6th resistance R6, the 5th resistance R5's is another
End, the 4th electric capacity C4 one end, the anode connection of the negative electrode of the first diode and the second diode and its connection end are second to adopt
The output end of collector, the 6th resistance the R6 other end, the 4th electric capacity C4 other end and the anode of the first diode are grounded,
The negative electrode access 3.3V voltages of second diode.
In the present embodiment, as shown in figure 3, the 3rd Acquisition Circuit includes the position sensor being arranged on climbing frame and the second letter
Number modulate circuit, secondary signal modulate circuit include the 7th resistance R7, the 8th resistance R8, the 5th electric capacity C5, the 3rd diode and
4th diode, one end connection of position sensor, the 7th resistance R7 one end and the 8th resistance R8, the 7th resistance R7's is another
End, the 5th electric capacity C5 one end, the anode connection of the negative electrode of the 3rd diode and the 4th diode and its connection end are the 3rd to adopt
The output end of collector, the 8th resistance the R8 other end, the 5th electric capacity C5 other end and the anode of the 3rd diode are grounded,
The negative electrode access 3.3V voltages of 4th diode.
In the present embodiment, as shown in figure 3, central processing unit is also associated with storage circuit, storage circuit includes model
AT24C64 the 3rd chip U3, the 9th resistance R9 and the tenth resistance R10, the 3rd chip U3 A0 pin, A1 pin, A2 pin, GND pin
It is grounded, one end connection of the 3rd chip U3 VCC pin, the 9th resistance R9 one end and the tenth resistance R10 and accesses with WP pin
3.3V voltages, the PB6 pin connection of the 9th resistance R9 other end, the 3rd chip U3 SCL pin and the first chip U1, the tenth resistance
The PB7 pin connection of the R10 other end, the 3rd chip U3 SDA pin and the first chip U1.
In the present embodiment, as shown in figure 3, central processing unit is also associated with for being communicated with external data receiver
Data transmission circuit, CAN transceiver U4, the 11st resistance R11 of data transmission circuit including model SN65HVD230 and the
12 resistance R12, CAN transceiver U4 D pin and the first chip U1 PA12 pin connection, CAN transceiver U4 R pin and the first core
Piece U1 PA11 pin connection, CAN transceiver U4 VCC pin access 3.3V voltages, CAN transceiver U4 GND pin and RS pin connect
Ground, one end connection of CAN transceiver U4 CANH pin and the 11st resistance R11, CAN transceiver U4 CANL pin and the 12nd electricity
R12 one end connection is hindered, the 11st resistance R11 other end and the 12nd resistance R12 other end are the defeated of CAN transceiver U4
Go out end.
In the present embodiment, as shown in figure 3, central processing unit is also associated with display screen L1, display screen L1 is used to show center
Data in processor, display screen L1 is the LCD display of dot matrix, the first chip U1 PB8 pin, PB9 pin, PB10 pin,
PB11 pin, PB12 pin, PB13 pin, PB14 pin, PB15 pin, PC0 pin, PC3 pin, PC4 pin, PC5 pin, PC6 pin, PC7 pin and PC8 pin
It is connected with display screen L1.
A kind of course of work of climbing frame condition checkout gear of the present embodiment is：Obliquity sensor obtains the anteversion and retroversion of climbing frame
Angle signal and left and right dip angle signal, front and rear dip angle signal and left and right dip angle signal are data signals, straight by serial port connector
Connect defeated into central processing unit；Gravity sensor is detected and obtains the gravitational cue of climbing frame, and position sensor is detected and obtained and climbs
The altitude signal of frame, gravitational cue and altitude signal are all 4-20mA current signals, and gravitational cue passes through the first signal condition
Circuit is handled, and the gravitational cue of current signal form is converted into voltage signal and handled to center by the first signal conditioning circuit
Device, altitude signal is handled by secondary signal modulate circuit, and secondary signal modulate circuit is by the high-tensile strength of current signal form
Signal is converted into voltage signal to central processing unit, and the rate of change of central processing unit computed altitude, the rate of change of height is to climb
The rate of climb of frame.Place is normalized in the front and rear inclination angle of climbing frame, left and right inclination angle, gravity and the rate of climb by central processing unit
Reason, obtains the front and rear inclination angle normalization data, the left and right inclination angle normalization data of climbing frame, the gravity normalization data of climbing frame of climbing frame
With the rate of climb normalization data of climbing frame.Using the front and rear inclination angle normalization data of climbing frame as climbing frame front and rear inclination angle detection number
According to xi1, the left and right inclination angle normalization data of climbing frame as climbing frame left and right inclination angle detection data xi2, the gravity normalization number of climbing frame
Data x is detected according to as the gravity of climbing framei3With the rate of climb normalization data of climbing frame number is detected as the rate of climb of climbing frame
According to xi4It is input in the input layer of neural network model, the hidden layer and output layer of neural network model are transmitted according to it successively
Function is calculated, and obtains the output y of neural network model, and the size finally according to y values judges climbing frame state, if y's takes
When value is less than 0.60, climbing frame state is safety, and central processing unit driving green indicating lamp lights；If y value is more than or equal to
0.60 and less than 0.85 when, climbing frame state for warning, central processing unit driving alarm send alarm；If y value is more than
During equal to 0.85 and less than or equal to 1, climbing frame state is danger, while central processing unit driving alarm sends alarm driving after
Electrical equipment, which disconnects, makes climbing frame stop motion.The specific work process of the climbing frame condition checkout gear of the present embodiment is as shown in Figure 4.
Claims (9)
1. a kind of climbing frame condition detection method, it is characterised in that comprise the following steps：
1. neural network model is built, described neural network model includes input layer, hidden layer and output layer；
Described input layer is used for input data, and the input vector of described input layer is Xi=[xi1 xi2 xi3 xi4], wherein,
xi1Represent the front and rear inclination angle detection data of climbing frame, xi2Represent the left and right inclination angle detection data of climbing frame, xi3Represent the gravity inspection of climbing frame
Survey data, xi4Represent the rate of climb detection data of climbing frame；
Described hidden layer includes ten neuron nodes, and described hidden layer is used for the input number for receiving described input layer
According to the transfer function of the neuron node of described hidden layer is f1(x), f1(x) it is tansig functions,E is the truth of a matter of natural logrithm, e=2.718281828459；The output of described hidden layerW1For the weight matrix of hidden layer, the transposition of subscript T representing matrixs, b1For the threshold value square of hidden layer
Battle array, W1And b1It is expressed as respectively with the form of matrix：
Described output layer receives described hidden layer output, and described output layer includes a neuron node, and described is defeated
The transfer function for going out the neuron node of layer is f2(x), f2(x) it is purelin functions, f2(x)=x；Described output layer it is defeated
Go outWherein, W2For the weight matrix of output layer, b2For output layer
Threshold matrix, W2And b2It is expressed as respectively with the form of matrix：
W2=[- 0.2282 1.1340-0.6504-0.1181-0.0120 0.2103 0.8087-0.5868 0.0913-
0.5395]
b2=[0.6769]；
The output y=o of described neural network model2；
2. the front and rear inclination angle, left and right inclination angle, four parameters of gravity and the rate of climb of climbing frame are gathered and obtained in real time；
3. transfer function is passed throughThe front and rear inclination angle of the climbing frame 2. obtained to step respectively, left and right inclination angle, gravity
It is normalized with four parameters of the rate of climb, respectively obtains front and rear inclination angle normalization data, the left and right of climbing frame of climbing frame
The rate of climb normalization data of inclination angle normalization data, the gravity normalization data of climbing frame and climbing frame, wherein x* is corresponded to respectively
Front and rear inclination angle, left and right inclination angle, the normalization data of four parameters of gravity and the rate of climb；X corresponds to climbing of 2. obtaining of step respectively
The front and rear inclination angle of frame, left and right inclination angle, four parameters of gravity and the rate of climb, max respectively correspond to the front and rear inclination angle of climbing frame, climbing frame
The maximum that four parameters of the rate of climb at left and right inclination angle, the gravity of climbing frame and climbing frame can reach, min is corresponded to before climbing frame respectively
The minimum value that back rake angle, the left and right inclination angle of climbing frame, four parameters of the rate of climb of the gravity of climbing frame and climbing frame can reach；
4. using the front and rear inclination angle normalization data of climbing frame as climbing frame front and rear inclination angle detection data xi1, the left and right inclination angle of climbing frame is returned
One changes data as the left and right inclination angle detection data x of climbing framei2, the gravity normalization data of climbing frame detects number as the gravity of climbing frame
According to xi3With the rate of climb normalization data of climbing frame data x is detected as the rate of climb of climbing framei4It is input to neural network model
Input layer in, calculate and obtain the output y of neural network model；
5. the output y of neural network model is made decisions, decision function is as follows：
If y value is less than 0.60, climbing frame state is safety；If y value is more than or equal to 0.60 and is less than 0.85,
Climbing frame state is warning；If y value is more than or equal to 0.85 and is less than or equal to 1, climbing frame state is danger.
2. a kind of climbing frame condition checkout gear, it is characterised in that including central processing unit, for gathering inclination angle and a left side before and after climbing frame
First Acquisition Circuit at Right deviation angle, for gathering the second Acquisition Circuit of climbing frame gravity, being adopted for gathering the 3rd of climbing frame position the
Collector, green indicating lamp, relay and alarm, described central processing unit respectively with the first described Acquisition Circuit, institute
The second Acquisition Circuit for stating, described the 3rd Acquisition Circuit, described green indicating lamp, described relay and described alarm
Device is connected, and is provided with neural network model in described central processing unit, and described neural network model includes input layer, hidden
Hide layer and output layer；
Described input layer is used for input data, and the input vector of described input layer is Xi=[xi1 xi2 xi3 xi4], wherein,
xi1Represent the front and rear inclination angle detection data of climbing frame, xi2Represent the left and right inclination angle detection data of climbing frame, xi3Represent the gravity inspection of climbing frame
Survey data, xi4Represent the rate of climb detection data of climbing frame；
Described hidden layer includes ten neuron nodes, and described hidden layer is used for the input number for receiving described input layer
According to the transfer function of the neuron node of described hidden layer is f1(x), f1(x) it is tansig functions,E is the truth of a matter of natural logrithm, e=2.718281828459；The output of described hidden layerWherein W1For the weight matrix of hidden layer, the transposition of subscript T representing matrixs, b1For the threshold value of hidden layer
Matrix, W1And b1It is expressed as respectively with the form of matrix：
Described output layer receives described hidden layer output, and described output layer includes a neuron node, and described is defeated
The transfer function for going out the neuron node of layer is f2(x), f2(x) it is purelin functions, f2(x)=x；Described output layer it is defeated
Go outWherein, W2For the weight matrix of output layer, b2For output layer
Threshold matrix, W2And b2It is expressed as respectively with the form of matrix：
W2=[- 0.2282 1.1340-0.6504-0.1181-0.0120 0.2103 0.8087-0.5868 0.0913-
0.5395]
b2=[0.6769]；
The output y=o of described neural network model2；
The first described Acquisition Circuit gathers the front and rear inclination angle and left and right inclination angle of climbing frame and sends described center processing in real time
Device, the second described Acquisition Circuit gathers the gravity of climbing frame and sends described central processing unit in real time, and the described 3rd adopts
Collector gathers the position of climbing frame and sends described central processing unit in real time, and described central processing unit is by described climbing frame
Change in location be converted to the rate of climb of climbing frame, described central processing unit respectively by the front and rear inclination angle of climbing frame, left and right inclination angle,
Four parameters of gravity and the rate of climb use transfer functionIt is normalized, respectively obtains climbing frame
Front and rear inclination angle normalization data, the left and right inclination angle normalization data of climbing frame, the gravity normalization data of climbing frame and the rising of climbing frame
Speed normalization data, wherein x*Inclination angle, left and right inclination angle, the normalization of four parameters of gravity and the rate of climb before and after corresponding to respectively
Data；X corresponds to the front and rear inclination angle, left and right inclination angle, four parameters of gravity and the rate of climb of climbing frame respectively, and max corresponds to climbing frame respectively
Front and rear inclination angle, the maximum that can reach of the left and right inclination angle of climbing frame, four parameters of the rate of climb of the gravity of climbing frame and climbing frame,
Min corresponds to four parameter energy of the rate of climb of front and rear inclination angle, the left and right inclination angle of climbing frame, the gravity of climbing frame and the climbing frame of climbing frame respectively
The minimum value reached；Using the front and rear inclination angle normalization data of climbing frame as climbing frame front and rear inclination angle detection data xi1, a left side for climbing frame
Right deviation angle normalization data as climbing frame left and right inclination angle detection data xi2, the gravity normalization data of climbing frame as climbing frame weight
Power detection data xi3With the rate of climb normalization data of climbing frame data x is detected as the rate of climb of climbing framei4It is input to nerve
In the input layer of network model, the output y for obtaining neural network model is calculated, if y value is less than 0.60, climbing frame state
For safety, the described green indicating lamp of described central processing unit driving lights；If y value is more than or equal to 0.60 and is less than
When 0.85, climbing frame state is warning, and the described alarm of described central processing unit driving sends alarm；If y value is big
When equal to 0.85 and less than or equal to 1, climbing frame state is danger, and the described alarm of described central processing unit driving sends police
Driving described relay to disconnect while report makes climbing frame stop motion.
3. a kind of climbing frame condition checkout gear according to claim 2, it is characterised in that described central processing unit includes
Model STM32F103RBT6 the first chip, model ULN2003 the second chip, serial port connector, first resistor,
Two resistance, 3rd resistor, the 4th resistance, the first electric capacity, the second electric capacity, the 3rd electric capacity, crystal oscillator and switch, the first described chip
PC1 pin be connected with the output end of the 3rd described Acquisition Circuit, the PC2 pin of described the first chip and the second described collection
The output end connection of circuit, the PA9 pin and PA10 pin of described the first chip pass through serial port connector and the first described collection
Circuit is connected, and the IN1 pin of the PA3 pin of described the first chip and the second described chip are connected by described first resistor,
The IN3 pin of the PA2 pin of the first described chip and the second described chip are connected by described second resistance, and described first
The IN5 pin of the PA1 pin of chip and the second described chip are connected by described 3rd resistor, the VDD of described the first chip
One end connection of pin, VDDA pin and the 4th described resistance and access 3.3V voltages, it is the other end of described the 4th resistance, described
The NRST pin of the first chip, one end connection of one end of described first electric capacity and described switch, described switch it is another
One end, the other end of the first described electric capacity, the B00T0 pin of the first described chip, BOOT1 pin, VSS pin and VSSA pin are equal
Ground connection, one end connection of the OSCIN pin of described the first chip, one end of the second described electric capacity and described crystal oscillator is described
The OSCOUT pin of the first chip, the other end connection of one end of described 3rd electric capacity and described crystal oscillator, described second
The other end of the other end of electric capacity and the 3rd described electric capacity is grounded, and the COM pin of the second described chip access 24V voltages.
4. a kind of climbing frame condition checkout gear according to claim 3, it is characterised in that the first described Acquisition Circuit bag
Obliquity sensor is included, described obliquity sensor is arranged on climbing frame.
5. a kind of climbing frame condition checkout gear according to claim 3, it is characterised in that the second described Acquisition Circuit bag
The gravity sensor and the first signal conditioning circuit on climbing frame are included, the first described signal conditioning circuit includes the 5th electricity
Resistance, the 6th resistance, the 4th electric capacity, the first diode and the second diode, described gravity sensor, described the 5th resistance
One end and the connection of one end of the 6th described resistance, the other end of described the 5th resistance, one end of the 4th described electric capacity, institute
The anode of the negative electrode for the first diode stated and the second described diode is connected and its connection end is the second described collection electricity
The output end on road, the other end of described the 6th resistance, the other end of the 4th described electric capacity and the first described diode
Anode is grounded, and the negative electrode of the second described diode accesses 3.3V voltages.
6. a kind of climbing frame condition checkout gear according to claim 3, it is characterised in that the 3rd described Acquisition Circuit bag
The position sensor and secondary signal modulate circuit on climbing frame are included, described secondary signal modulate circuit includes the 7th electricity
Resistance, the 8th resistance, the 5th electric capacity, the 3rd diode and the 4th diode, described position sensor, described the 7th resistance
One end and the connection of one end of the 8th described resistance, the other end of described the 7th resistance, one end of the 5th described electric capacity, institute
The anode of the negative electrode for the 3rd diode stated and the 4th described diode is connected and its connection end is the 3rd described collection electricity
The output end on road, the other end of described the 8th resistance, the other end of the 5th described electric capacity and the 3rd described diode
Anode is grounded, and the negative electrode of the 4th described diode accesses 3.3V voltages.
7. a kind of climbing frame condition checkout gear according to claim 3, it is characterised in that described central processing unit also connects
Storage circuit is connected to, described storage circuit includes model AT24C64 the 3rd chip, the 9th resistance and the tenth resistance, institute
A0 pin, A1 pin, A2 pin, GND pin and the WP pin for the 3rd chip stated are grounded, the VCC pin of described the 3rd chip, described
One end of nine resistance and the connection of one end of the tenth described resistance and access 3.3V voltages, the other end of described the 9th resistance,
The PB6 pin connection of the SCL pin of the 3rd described chip and the first described chip, it is the other end of described the tenth resistance, described
The 3rd chip SDA pin and described the first chip the connection of PB7 pin.
8. a kind of climbing frame condition checkout gear according to claim 3, it is characterised in that described central processing unit also connects
The data transmission circuit for being communicated with external data receiver is connected to, described data transmission circuit includes model
SN65HVD230 CAN transceiver, the 11st resistance and the 12nd resistance, the D pin and described of described CAN transceiver
The PA11 pin connection of the PA12 pin connection of one chip, the R pin of described CAN transceiver and the first described chip, described CAN
The VCC pin access 3.3V voltages of transceiver, the GND pin and RS pin of described CAN transceiver are grounded, described CAN transceiver
CANH pin and described the 11st resistance one end connection, the CANL pin and the 12nd described electricity of described CAN transceiver
The other end of one end connection of resistance, the other end of described the 11st resistance and the 12nd described resistance is received for described CAN
Send out the output end of device.
9. a kind of climbing frame condition checkout gear according to claim 3, it is characterised in that described central processing unit also connects
Display screen is connected to, described display screen is used to show the data in described central processing unit, and described display screen is dot matrix
LCD display, the PB8 pin of described the first chip, PB9 pin, PB10 pin, PB11 pin, PB12 pin, PB13 pin, PB14 pin,
PB15 pin, PC0 pin, PC3 pin, PC4 pin, PC5 pin, PC6 pin, PC7 pin and PC8 pin are connected with described display screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410733786.8A CN105243253B (en) | 2014-12-05 | 2014-12-05 | A kind of climbing frame condition detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410733786.8A CN105243253B (en) | 2014-12-05 | 2014-12-05 | A kind of climbing frame condition detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105243253A CN105243253A (en) | 2016-01-13 |
| CN105243253B true CN105243253B (en) | 2017-10-03 |
Family
ID=55040901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410733786.8A Active CN105243253B (en) | 2014-12-05 | 2014-12-05 | A kind of climbing frame condition detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105243253B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110207871B (en) * | 2018-02-28 | 2021-04-06 | 新疆金风科技股份有限公司 | Method, device, storage medium and system for stress prediction of wind turbine generator |
| CN109558807B (en) * | 2018-11-08 | 2021-10-08 | 深圳市特辰科技股份有限公司 | Climbing frame image identification safety protection system and method |
| CN110736980B (en) * | 2019-11-04 | 2021-09-21 | 广东博智林机器人有限公司 | Method, device and system for monitoring state information of climbing frame |
| CN113958107B (en) * | 2020-11-25 | 2023-03-21 | 广州三叠纪元智能科技有限公司 | Climbing frame control method, electric box, server and storage medium |
| CN114659559B (en) * | 2022-03-28 | 2022-12-09 | 江苏鑫昇腾科技发展股份有限公司 | Intelligent building climbing frame working state monitoring system and method based on Internet of things |
| CN115560728B (en) * | 2022-12-07 | 2023-02-03 | 北京城建华晟交通建设有限公司 | Column plate type hollow high pier construction hydraulic climbing frame stroke balance monitoring equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202577929U (en) * | 2012-01-16 | 2012-12-05 | 蚌埠高灵传感系统工程有限公司 | Novel climbing frame intelligent synchronous control device |
| CN103760299A (en) * | 2013-04-25 | 2014-04-30 | 孝感毅恒安全科技有限公司 | Comprehensive air quality prediction method based on two-stage neural network |
-
2014
- 2014-12-05 CN CN201410733786.8A patent/CN105243253B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202577929U (en) * | 2012-01-16 | 2012-12-05 | 蚌埠高灵传感系统工程有限公司 | Novel climbing frame intelligent synchronous control device |
| CN103760299A (en) * | 2013-04-25 | 2014-04-30 | 孝感毅恒安全科技有限公司 | Comprehensive air quality prediction method based on two-stage neural network |
Non-Patent Citations (3)
| Title |
|---|
| Convergence analysis of online gradient method for BP neural networks;Wei Wu et al.;《Neural Networks》;20111231;第24卷;第91-98页 * |
| 基于多传感器数据融合的火灾报警系统设计;吴晓方 等;《齐齐哈尔大学学报》;20110930;第27卷(第5期);第11-13页 * |
| 导轨式爬架技术在高层建筑工程中的应用;丁晓;《山西建筑》;20120131;第38卷(第3期);第105-106页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105243253A (en) | 2016-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105243253B (en) | A kind of climbing frame condition detection method and device | |
| CN110264672A (en) | A kind of early warning system of geological disaster | |
| CN106836776A (en) | Intelligent climbing frame control system and control method | |
| CN108000561A (en) | Intelligent robot and its anticollision prevent falling device | |
| CN110047290A (en) | Highway Maintenance and accident treatment safety pre-warning system | |
| CN106310665A (en) | Robot used for martial arts arena contest | |
| CN107085920A (en) | A kind of fireman's sign monitoring method and system | |
| CN206107557U (en) | Unmanned aerial vehicle for remote sensing fire control detection | |
| CN206930763U (en) | A kind of lithium battery parameter acquisition system | |
| CN107074347A (en) | Flight control method, system and unmanned vehicle | |
| CN106523033A (en) | Efficient coal mine safety monitoring system | |
| CN107369291A (en) | The anti-external force damage alarm system and method for high-tension line based on deep learning | |
| CN103171561B (en) | Automobile attitude detecting method | |
| CN207096773U (en) | A kind of cargo hold level monitoring system based on Redundant Control | |
| CN105403198B (en) | A kind of real-time monitoring platform of iron tower of power transmission line gradient | |
| CN101590644B (en) | Node device of wireless mobile sensor network | |
| CN104330145A (en) | Railway container overload and unbalanced load detection monitoring system | |
| CN116436157A (en) | System and method for detecting state of power grid equipment under extreme descent | |
| CN103761828A (en) | Early warning method for fire disaster in passenger car engine cabin | |
| CN205791642U (en) | A kind of battery system with falling guard function | |
| CN207300584U (en) | A kind of used car intelligent detection device | |
| CN207200818U (en) | A kind of Shatter-resistant device and smart machine for smart machine | |
| CN102622851B (en) | Fire-fighting individual-soldier posture sensing device | |
| CN105488959B (en) | A kind of real-time flood control system of intelligence and method | |
| CN205898189U (en) | Check out test set and system are strikeed to wearing formula |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |