CN113568812A

CN113568812A - State detection method and device for intelligent robot

Info

Publication number: CN113568812A
Application number: CN202110862083.5A
Authority: CN
Inventors: 吴警
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2021-07-29
Filing date: 2021-07-29
Publication date: 2021-10-29
Anticipated expiration: 2041-07-29
Also published as: CN113568812B

Abstract

The embodiment of the invention provides a state detection method and a state detection device for an intelligent robot, wherein the method comprises the following steps: acquiring current first equipment state data of an intelligent robot to be detected; wherein the first device state data comprises: receiving the time length between the moment of sending the heartbeat message last time and the current moment, the occupancy rate of a memory and the utilization rate of a CPU; determining whether the current equipment performance of the intelligent robot is in an abnormal state or not according to the first equipment state data and a preset abnormal working state identification condition; and if the current equipment performance of the intelligent robot is in an abnormal state, alarming in a first alarming mode. The method provided by the embodiment of the invention can effectively detect whether the equipment performance of the intelligent robot is in an abnormal state or not, and can give an alarm in the abnormal state.

Description

State detection method and device for intelligent robot

Technical Field

The invention relates to the technical field of intelligent machines, in particular to a state detection method and device of an intelligent robot.

Background

With the rapid development of industrial technology, intelligent robots can be used to replace people in industrial production to perform certain long-time operations which are monotonous, frequent and repeated, or operations in dangerous and harsh environments. For example, in the processes of machining, metal product industry, simple assembly and the like, the intelligent robot can be used for completing corresponding process operations.

In order to ensure the production sequence, the health state of the intelligent robot needs to be detected to determine the current working state of the intelligent robot, and then the intelligent robot can be timely maintained according to the current working state of the intelligent robot.

Disclosure of Invention

An object of the embodiments of the present invention is to provide a method and an apparatus for detecting a state of an intelligent robot, which can effectively detect whether a device performance of the intelligent robot is in an abnormal state, and can alarm in the abnormal state. The specific technical scheme is as follows:

in a first aspect of the present invention, there is provided a method for detecting a state of an intelligent robot, the method including:

acquiring current first equipment state data of an intelligent robot to be detected; wherein the first device state data comprises: receiving the time length between the moment of sending the heartbeat message last time and the current moment, the occupancy rate of a memory and the utilization rate of a CPU;

determining whether the current equipment performance of the intelligent robot is in an abnormal state or not according to the first equipment state data and a preset abnormal working state identification condition;

and if the current equipment performance of the intelligent robot is in an abnormal state, alarming in a first alarming mode.

Optionally, determining whether the current device performance of the intelligent robot is in an abnormal state according to the first device state data and a preset abnormal working state identification condition, includes:

normalizing the first equipment state data to obtain a corresponding characteristic vector serving as a first characteristic vector to be detected;

calculating the similarity between the first to-be-detected feature vector and a first abnormal feature vector corresponding to the preset abnormal equipment performance;

if the calculated similarity is larger than a first threshold value, determining that the current equipment performance of the intelligent robot is in an abnormal state;

and if the calculated similarity is not greater than a first threshold value, determining that the current equipment performance of the intelligent robot is in a non-abnormal state.

Optionally, the method further includes:

when a preset detection period is reached, acquiring second equipment state data of the intelligent robot in the current detection period; wherein the second device status data comprises at least one of: the current environment temperature of the intelligent robot, the current inclination angle of the intelligent robot and the specified detection parameters of the current detection period; the specified detection parameters of the current detection period are as follows: the displacement detection parameters are determined based on the displacement detection parameters of the last detection period and the displacement of the intelligent robot in the current detection period;

determining whether the current working environment of the intelligent robot is in an abnormal state or not based on the second equipment state data and a preset abnormal working environment recognition condition;

and if the current working environment of the intelligent robot is in an abnormal state, giving an alarm in a second alarm mode.

Optionally, determining whether the current working environment of the intelligent robot is in an abnormal state based on the second device state data and a preset abnormal working environment recognition condition, including:

normalizing the second equipment state data to obtain a corresponding characteristic vector serving as a second characteristic vector to be detected;

calculating the similarity between the second characteristic vector to be detected and a second abnormal characteristic vector corresponding to a preset abnormal working environment;

if the calculated similarity is larger than a second threshold value, determining that the current working environment of the intelligent robot is in an abnormal state;

and if the calculated similarity is not greater than a second threshold value, determining that the current working environment of the intelligent robot is in a non-abnormal state.

Optionally, if the current working environment of the intelligent robot is in an abnormal state, the intelligent robot performs an alarm in a second alarm manner, including:

if the current working environment of the intelligent robot is in an abnormal state, broadcasting and sending a first alarm signal in a first preset range, so that alarm equipment in the first preset range alarms in a second alarm mode after receiving the first alarm signal;

if the first alarm releasing signal is not received within a first preset time after the first alarm signal is sent, broadcasting and sending the first alarm signal within a second preset range, so that the alarm equipment within the second preset range alarms in a second alarm mode after receiving the first alarm signal; wherein the second preset range is larger than the first preset range.

Optionally, the method further includes:

when a preset detection period is reached, acquiring an appointed detection parameter of the previous detection period as a first appointed detection parameter, and acquiring the displacement of the intelligent robot in the current detection period as a first displacement;

if the first displacement is smaller than a first preset distance, taking the sum of the first specified detection parameter and the first numerical value as the specified detection parameter of the current detection period;

if the first displacement is not smaller than a first preset distance and is smaller than a second preset distance, taking a first specified detection parameter as a specified detection parameter of the current detection period; wherein the first preset distance is smaller than the second preset distance;

and if the first displacement is not less than the second preset distance, setting the specified detection parameter of the current detection period as a preset numerical value indicating that the displacement of the intelligent robot is in a non-abnormal state.

Optionally, if the current device performance of the intelligent robot is in an abnormal state, the intelligent robot performs an alarm in a first alarm manner, including:

if the current equipment performance of the intelligent robot is in an abnormal state, broadcasting and sending a second alarm signal in a third preset range, so that the alarm equipment in the third preset range alarms in a first alarm mode after receiving the second alarm signal; sending a message to a preset mobile terminal, wherein the message indicates that the current equipment performance of the intelligent robot is in an abnormal state;

if a second alarm release signal is not received within a second preset time after the second alarm signal is sent, broadcasting and sending the second alarm signal within a fourth preset range, so that the alarm equipment within the fourth preset range alarms in a first alarm mode after receiving the second alarm signal; wherein the fourth preset range is greater than the third preset range.

In a second aspect of the present invention, there is also provided a state detection apparatus for an intelligent robot, the apparatus including:

the first equipment state data acquisition module is used for acquiring the current first equipment state data of the intelligent robot to be detected; wherein the first device state data comprises: receiving the time length between the moment of sending the heartbeat message last time and the current moment, the occupancy rate of a memory and the utilization rate of a CPU;

the equipment performance determining module is used for determining whether the current equipment performance of the intelligent robot is in an abnormal state or not according to the first equipment state data and a preset abnormal working state identification condition;

and the first alarm module is used for giving an alarm in a first alarm mode if the current equipment performance of the intelligent robot is in an abnormal state.

Optionally, the device performance determining module includes:

the first to-be-detected feature vector determining submodule is used for carrying out normalization processing on the first equipment state data to obtain a corresponding feature vector which is used as a first to-be-detected feature vector;

the first similarity determining submodule is used for calculating the similarity between the first to-be-detected feature vector and a first abnormal feature vector corresponding to the performance of preset abnormal equipment;

the device performance abnormal state determining submodule is used for determining that the current device performance of the intelligent robot is in an abnormal state if the calculated similarity is larger than a first threshold;

and the device performance non-abnormal state determining submodule is further used for determining that the current device performance of the intelligent robot is in a non-abnormal state if the calculated similarity is not greater than a first threshold.

Optionally, the apparatus further comprises:

the second equipment state data acquisition module is used for acquiring second equipment state data of the intelligent robot in the current detection period when the preset detection period is reached; wherein the second device status data comprises at least one of: the current environment temperature of the intelligent robot, the current inclination angle of the intelligent robot and the specified detection parameters of the current detection period; the specified detection parameters of the current detection period are as follows: the displacement detection parameters are determined based on the displacement detection parameters of the last detection period and the displacement of the intelligent robot in the current detection period;

the working environment determining module is used for determining whether the current working environment of the intelligent robot is in an abnormal state or not based on the second equipment state data and a preset abnormal working environment recognition condition;

and the second warning module is used for warning in a second warning mode if the current working environment of the intelligent robot is in an abnormal state.

Optionally, the work environment determining module includes:

the second to-be-detected feature vector determining submodule is used for carrying out normalization processing on the second equipment state data to obtain a corresponding feature vector which is used as a second to-be-detected feature vector;

the second similarity determining submodule is used for calculating the similarity between the second characteristic vector to be detected and a second abnormal characteristic vector corresponding to a preset abnormal working environment;

the working environment abnormal state determining submodule is used for determining that the current working environment of the intelligent robot is in an abnormal state if the calculated similarity is larger than a second threshold;

and the working environment non-abnormal state determining submodule is further used for determining that the current working environment of the intelligent robot is in a non-abnormal state if the calculated similarity is not greater than a second threshold.

Optionally, the second warning module is specifically configured to broadcast and send a first warning signal in a first preset range if the current working environment of the intelligent robot is in an abnormal state, so that after receiving the first warning signal, the warning device in the first preset range performs warning in a second warning manner;

Optionally, the apparatus further comprises:

the parameter acquisition module is used for acquiring the specified detection parameter of the previous detection period as a first specified detection parameter and acquiring the displacement of the intelligent robot in the current detection period as a first displacement when the preset detection period is reached;

the specified detection parameter determining module is used for taking the sum of the first specified detection parameter and the first numerical value as the specified detection parameter of the current detection period if the first displacement is smaller than the first preset distance;

the specified detection parameter determining module is further configured to use the first specified detection parameter as a specified detection parameter of the current detection period if the first displacement is not smaller than a first preset distance and is smaller than a second preset distance; wherein the first preset distance is smaller than the second preset distance;

the appointed detection parameter determining module is further configured to set the appointed detection parameter of the current detection period to a preset numerical value indicating that the displacement of the intelligent robot is in a non-abnormal state if the first displacement is not smaller than a second preset distance. Optionally, the first warning module is specifically configured to broadcast and send a second warning signal in a third preset range if the current device performance of the intelligent robot is in an abnormal state, so that the warning device in the third preset range performs warning in a first warning manner after receiving the second warning signal; sending a message to a preset mobile terminal, wherein the message indicates that the current equipment performance of the intelligent robot is in an abnormal state;

In yet another aspect of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the state detection method of the intelligent robot described above.

In yet another aspect of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, causes the computer to perform the state detection method of the intelligent robot as described in any one of the above.

By adopting the method provided by the embodiment of the invention, the current first equipment state data of the intelligent robot to be detected is acquired; wherein the first device state data comprises: receiving the time length between the moment of sending the heartbeat message last time and the current moment, the occupancy rate of a memory and the utilization rate of a CPU; determining whether the current equipment performance of the intelligent robot is in an abnormal state or not according to the first equipment state data and a preset abnormal working state identification condition; and if the current equipment performance of the intelligent robot is in an abnormal state, alarming in a first alarming mode.

The method provided by the embodiment of the invention can effectively detect whether the equipment performance of the intelligent robot is in an abnormal state or not, and can give an alarm in the abnormal state.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.

Fig. 1 is a flowchart of a state detection method for an intelligent robot according to an embodiment of the present invention;

FIG. 2 is a flow chart of another method for detecting the status of an intelligent robot according to an embodiment of the present invention;

FIG. 3 is a flowchart of a method for detecting a working environment of an intelligent robot according to an embodiment of the present invention;

FIG. 4 is a flowchart of another method for detecting a working environment of an intelligent robot according to an embodiment of the present invention;

FIG. 5 is a flow chart of another method for detecting a working environment of an intelligent robot according to an embodiment of the present invention;

FIG. 6 is a flowchart of a method for obtaining specified detection parameters according to an embodiment of the present invention;

FIG. 7 is a flowchart illustrating another method for detecting the status of an intelligent robot according to an embodiment of the present invention;

fig. 8 is a flowchart illustrating an exemplary method for detecting a state of an intelligent robot according to an embodiment of the present invention;

fig. 9 is a schematic diagram illustrating a state detection principle of an intelligent robot according to an embodiment of the present invention;

fig. 10 is a structural diagram of a state detecting apparatus of an intelligent robot according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.

The invention provides a state detection method of an intelligent robot. The method can be applied to detection equipment for detecting the state of the intelligent robot. For example, the detection device may be built in the intelligent robot to be detected, or may be a device independent from the intelligent robot and capable of performing data communication with the intelligent robot.

Referring to fig. 1, fig. 1 is a flowchart of a state detection method for an intelligent robot according to an embodiment of the present invention, where the method may include the following steps:

s101: acquiring current first equipment state data of the intelligent robot to be detected.

Wherein the first device state data comprises: the time length between the moment of receiving the last heartbeat message and the current moment, the occupancy rate of the memory and the utilization rate of the CPU.

S102: and determining whether the current equipment performance of the intelligent robot is in an abnormal state or not according to the first equipment state data and a preset abnormal working state identification condition.

S103: and if the current equipment performance of the intelligent robot is in an abnormal state, alarming in a first alarming mode.

In step S101, in an implementation manner, the intelligent robot may be preset to send a heartbeat message to the detection device in a cycle of a first predetermined time period, for example, the first predetermined time period may be 10 minutes or 20 minutes, but is not limited thereto.

In addition, the detection device may also acquire the first device state data of the intelligent robot with the second predetermined time period as a cycle. And the second preset time length is not more than the first preset time length. For example, if the first predetermined time period is 10 minutes, the second predetermined time period is 8 minutes; the first preset time period is 20 minutes, and the second preset time period is 15 minutes, but not limited thereto.

For example, when receiving a heartbeat message, the detection device may start timing, and if the heartbeat message is received again, the detection device may restart timing to obtain a time length between the time when the heartbeat message was received last time and the current time.

In step S102, a preset abnormal operating state identification condition may be used to determine whether the first device state data is abnormal, for example, based on the abnormal operating state identification condition, a probability that the first device state data is abnormal may be calculated, and further, based on the probability, it may be determined whether the current device performance of the intelligent robot is in an abnormal state.

For example, a plurality of correspondence relationships may be set in advance, including:

1. a correspondence (which may be referred to as a first correspondence) between the timeout period and the probability (which may be referred to as a first probability) that the device performance is in an abnormal state is set. The timeout duration represents a time duration between the time when the heartbeat message is received last time and the current time, and is different from a first predetermined time duration (which may be referred to as a first difference t). For example, the first relationship can be seen in table (1).

Watch (1)

Based on table (1), it can be seen that the larger the first difference value is, the larger the first probability is, which indicates that the intelligent robot has a higher probability of failure.

2. A correspondence (which may be referred to as a second correspondence) between the occupancy rate of the memory (hereinafter, denoted by R) and the probability (which may be referred to as a second probability) that the device performance is in an abnormal state is set. For example, the second relationship can be seen in table (2).

Watch (2)

Based on the table (2), it can be seen that the higher the occupancy rate of the memory is, the higher the second probability is, which indicates that the probability of the intelligent robot failing is higher.

3. A correspondence relationship (which may be referred to as a third correspondence relationship) between the usage rate of the CPU (hereinafter, denoted by C) and the probability that the device performance is in an abnormal state (which may be referred to as a third probability) is set. For example, the third relationship can be seen in table (3).

Watch (3)

CPU utilization rate C	Third probability	CPU utilization rate C	Third probability
				50％＜C≤55％	0.1	55％＜C≤60％	0.2
60％＜C≤65％	0.3	65％＜C≤70％	0.4
				70％＜C≤75％	0.5	75％＜C≤80％	0.6
80％＜C≤85％	0.7	85％＜C≤90％	0.8
				90％＜C≤95％	0.9	95％＜C≤100％	1
C≤50％	0

As can be seen from table (3), the higher the CPU utilization rate, the higher the third probability, which indicates that the intelligent robot has a higher probability of failure.

Based on the first corresponding relationship, the second corresponding relationship and the third corresponding relationship, a corresponding first probability, a corresponding second probability and a corresponding third probability can be determined.

Further, whether the current device performance of the intelligent robot is in an abnormal state or not can be determined based on the first probability, the second probability and the third probability.

For example, when at least one of the three probabilities is greater than a performance abnormality threshold (e.g., may be 0.5), it may be determined that the current device performance of the intelligent robot is in an abnormal state.

In addition, if none of the three probabilities is greater than the performance abnormity threshold, the current equipment performance of the intelligent robot can be determined to be in a non-abnormal state.

Alternatively, a weighted sum of the three probabilities may be calculated based on a preset weight to obtain the first numerical value.

Further, if the first value is greater than the performance anomaly weighting threshold (for example, may be 0.5), it may be determined that the current device performance of the intelligent robot is in an abnormal state.

Otherwise, if the first value is not greater than the performance abnormality weighting threshold, it may be determined that the current device performance of the intelligent robot is in a non-abnormal state.

In step S103, in an implementation manner, in an environment where the intelligent robot works, a plurality of alarm devices may be deployed, each alarm device may include a buzzer and a two-color alarm lamp, and when it is detected that the current device performance of the intelligent robot is in an abnormal state, the alarm devices may be controlled to alarm.

The first alarm mode may be: the buzzer gives out an alarm and the double-color alarm lamp lights up a red light.

In one embodiment, referring to fig. 2, on the basis of fig. 1, step S102 may include:

s1021: and normalizing the first equipment state data to obtain a corresponding characteristic vector as a first characteristic vector to be detected.

S1022: and calculating the similarity between the first to-be-detected feature vector and a first abnormal feature vector corresponding to the preset abnormal equipment performance.

S1023: and if the calculated similarity is larger than a first threshold value, determining that the current equipment performance of the intelligent robot is in an abnormal state.

S1024: and if the calculated similarity is not greater than the first threshold value, determining that the current equipment performance of the intelligent robot is in a non-abnormal state.

The first threshold may be set by a technician empirically, for example, the first threshold may be set to 0.5, 0.6, but is not limited thereto.

In one implementation, the duration between the time when the heartbeat message was last sent and the current time is received, the occupancy rate of the memory, and the utilization rate of the CPU may be normalized to values in the range of 0 to 1. Correspondingly, the first abnormal feature vector corresponding to the preset abnormal device performance is (1,1, 1).

In one implementation, the similarity between the first to-be-detected feature vector and the first abnormal feature vector may be calculated by a vector similarity calculation formula. The vector similarity calculation formula may be a cosine similarity (cosine) formula, an Euclidean distance (Euclidean) formula, a Manhattan distance (Manhattan distance) formula, or the like, and is not limited herein.

In another way, a Vector Space Model (VSM) may be used to calculate the similarity between the first to-be-detected feature Vector and the first abnormal feature Vector.

In one embodiment, it may be further determined whether the working environment of the intelligent robot is in an abnormal state, referring to fig. 3, the method may further include the steps of:

s301: and when the preset detection period is reached, acquiring second equipment state data of the intelligent robot in the current detection period.

Wherein the second device status data comprises at least one of: the method comprises the following steps of (1) setting the current ambient temperature of the intelligent robot, the current inclination angle of the intelligent robot and specified detection parameters of the current detection period; the specified detection parameters of the current detection period are as follows: and determining based on the displacement detection parameters of the last detection period and the displacement of the intelligent robot in the current detection period.

S302: and determining whether the current working environment of the intelligent robot is in an abnormal state or not based on the second equipment state data and the preset abnormal working environment recognition condition.

S303: and if the current working environment of the intelligent robot is in an abnormal state, giving an alarm in a second alarm mode.

In the embodiment of the invention, the intelligent robot is provided with the temperature sensor, the level gauge and the displacement sensor, and the current environment temperature of the intelligent robot, the current inclination angle of the intelligent robot and the displacement of the intelligent robot in the current detection period can be obtained through the sensors.

The preset abnormal working environment recognition condition may be used to determine whether the second device status data is abnormal, for example, based on the abnormal working environment recognition condition, the probability that the second device status data is abnormal may be calculated, and then, whether the current working environment of the intelligent robot is in an abnormal state may be determined.

1. and the corresponding relation (which can be called as a fourth corresponding relation) between the current ambient temperature T of the intelligent robot and the probability (which can be called as a fourth probability) that the working environment is in an abnormal state. For example, the fourth relationship can be seen in table (4).

Watch (4)

Based on table (4), it can be seen that the higher the ambient temperature is, the higher the fourth probability is, which also indicates that the probability of the working environment of the intelligent robot being abnormal is higher.

2. And the correspondence (which can be referred to as a fifth correspondence) between the current inclination angle F of the intelligent robot and the probability (which can be referred to as a fifth probability) that the working environment is in an abnormal state. For example, the fifth relationship can be seen in table (5).

Watch (5)

Inclination angle F (degree)	Fifth probability	Inclination angle F (degree)	Fifth probability
				10＜F≤15	0.1	15＜F≤20	0.2
20＜F≤25	0.3	25＜F≤30	0.4
				30＜F≤35	0.5	35＜F≤40	0.6
40＜F≤45	0.7	45＜F≤50	0.8
				50＜F≤55	0.9	F>55	1
F≤10	0

Based on table (5), it can be seen that the larger the inclination angle, the larger the fifth probability, which indicates that the probability of the working environment of the intelligent robot being abnormal is higher.

The specified detection parameter of the current detection period may represent a probability (may be referred to as a sixth probability) that the displacement of the intelligent robot is abnormal in the current detection period. The larger the specified detection parameter of the current detection period is, the larger the sixth probability is, the larger the probability that the current working environment of the robot is abnormal is.

In one implementation, the inverse of the displacement of the intelligent robot within the current detection period may be calculated. The larger the reciprocal is, the higher the probability of displacement abnormality is, the higher the probability of indicating that the current working environment of the robot is abnormal is.

Based on the fourth corresponding relationship, the fifth corresponding relationship and the specified detection parameters of the current detection period, a corresponding fourth probability, a corresponding fifth probability and a corresponding sixth probability can be determined.

Further, whether the current working environment of the intelligent robot is in an abnormal state or not can be determined based on the fourth probability, the fifth probability and the sixth probability.

For example, when at least one of the three probabilities is greater than an environmental anomaly threshold (e.g., may be 0.5), it may be determined that the current working environment of the intelligent robot is in an abnormal state.

In addition, if the three probabilities are not greater than the environmental anomaly threshold value, it can be determined that the current working environment of the intelligent robot is in a non-abnormal state.

Alternatively, a weighted sum of the three probabilities may be calculated based on preset weights to obtain the second numerical value.

Further, if the second value is greater than the environment abnormality weighting threshold (for example, may be 0.5), it may be determined that the current working environment of the intelligent robot is in an abnormal state.

Otherwise, if the second value is not greater than the environment abnormality weighting threshold, it may be determined that the current working environment of the intelligent robot is in a non-abnormal state.

In step S303, reference may be made to the description of step 103.

Wherein, the second alarm mode may be: the buzzer gives out an alarm and the double-color alarm lamp lights the yellow lamp.

The staff or the technician can distinguish different types of faults according to different alarm modes.

In one embodiment, referring to fig. 4, on the basis of fig. 3, step S302 may include:

s3021: and normalizing the second equipment state data to obtain a corresponding characteristic vector serving as a second characteristic vector to be detected.

S3022: and calculating the similarity between the second characteristic vector to be detected and a second abnormal characteristic vector corresponding to the preset abnormal equipment performance.

S3023: and if the calculated similarity is larger than a second threshold value, determining that the current equipment performance of the intelligent robot is in an abnormal state.

S3024: and if the calculated similarity is not greater than the second threshold, determining that the current equipment performance of the intelligent robot is in a non-abnormal state.

And normalizing the current environment temperature of the intelligent robot, the current inclination angle of the intelligent robot and the specified detection parameters of the current detection period into values within the range of 0-1. Correspondingly, the second abnormal feature vector corresponding to the preset abnormal device performance is (1,1, 1).

In one implementation, the similarity between the second feature vector to be detected and the second abnormal feature vector may be calculated by a vector similarity calculation formula. The vector similarity calculation formula may be a cosine similarity formula, an euclidean distance formula, a manhattan distance formula, or the like, and is not limited specifically herein.

In another way, a vector space model can be used to calculate the similarity between the second feature vector to be detected and the second abnormal feature vector.

The second threshold may be set by a worker based on experience, for example, the first threshold may be set to 0.5, 0.6, but is not limited thereto.

In one embodiment, referring to fig. 5, on the basis of fig. 3, step S303 may include:

s3031: if the current working environment of the intelligent robot is in an abnormal state, a first alarm signal is broadcast and sent within a first preset range, so that alarm equipment within the first preset range can give an alarm in a second alarm mode after receiving the first alarm signal.

S3032: and if the first alarm releasing signal is not received within the first preset time after the first alarm signal is sent, broadcasting and sending the first alarm signal within a second preset range, so that the alarm equipment within the second preset range alarms in a second alarm mode after receiving the first alarm signal.

Wherein the second preset range is larger than the first preset range.

In the embodiment of the present invention, the detection device may be provided with a short-range wireless communication module, where the short-range wireless communication module may be a ZigBee wireless communication module, a bluetooth wireless communication module, an infrared wireless communication module, a Wi-Fi wireless communication module, and the like, and is not limited herein.

By controlling the power of the short-range wireless communication module for transmitting information, the control of the range of the short-range wireless communication module for transmitting information can be realized.

In one implementation, after the alarm device in the first preset range receives the first alarm signal, the buzzer sends out an alarm and the two-color alarm lamp lights the yellow light. The detection device can be provided with a reset button for alarm release, and when a worker presses the reset button, the worker receives a first alarm release signal. If the first alarm removing signal is not received within the first preset time after the first alarm signal is sent, the power of the short-distance wireless communication module for sending information can be enhanced, alarm equipment in a farther range can give an alarm, and workers can find the alarm aiming at the intelligent robot more easily.

In another mode, after the alarm device in the first preset range receives the first alarm signal, the buzzer sends out an alarm at a first preset frequency and the double-color alarm lamp lights the yellow lamp.

The detection device can be provided with a reset button for alarm release, and when a worker presses the reset button, the worker receives a first alarm release signal. If the first alarm releasing signal is not received within the first preset time after the first alarm signal is sent, the power of the short-distance wireless communication module for sending information can be enhanced, and a third alarm signal is sent, so that alarm equipment in a farther range can give an alarm. The alarm aiming at the intelligent robot is easier to find by the staff.

The alarm device which receives the third alarm signal gives an alarm in a mode that the buzzer sends out an alarm at a second preset frequency and the double-color alarm lamp lights the yellow lamp, wherein the second preset frequency is greater than the first preset frequency.

In one embodiment, referring to fig. 6, the method of obtaining the specified detection parameters may include the steps of:

s601: and when the preset detection period is reached, acquiring the specified detection parameter of the previous detection period as a first specified detection parameter, and acquiring the displacement of the intelligent robot in the current detection period as a first displacement.

S602: if the first displacement is smaller than the first preset distance, taking the sum of the first specified detection parameter and the first numerical value as the specified detection parameter of the current detection period;

s603: if the first displacement is not smaller than the first preset distance and is smaller than the second preset distance, taking the first specified detection parameter as a specified detection parameter of the current detection period; wherein the first preset distance is smaller than the second preset distance;

s604: and if the first displacement is not less than the second preset distance, setting the specified detection parameter of the current detection period as a preset numerical value representing that the displacement of the intelligent robot is in a non-abnormal state.

In the embodiment of the present invention, since the specified detection parameter of each cycle is determined according to the specified detection parameter of the last week, it may be preset for the first cycle, and the specified detection parameter of the last cycle is a preset value (for example, may be 0).

Accordingly, the first preset distance and the second preset distance may be set according to specific functions of the intelligent robot, for example, the first preset distance is 0.5m, and the second preset distance is 1 m.

The specified detection parameter may be in a range from 0 to 1, and accordingly, the preset value may be 0, and the first value may be 0.1 or 0.2, but is not limited thereto.

The specified detection parameters of the current detection period can represent the probability of abnormal displacement of the intelligent robot in the current detection period. If the first displacement is smaller than the first preset distance, it indicates that the displacement of the intelligent robot in the current detection period is abnormal, and the value of the specified detection parameter can be increased, that is, the sum of the first specified detection parameter and the first value in the previous detection period is used as the specified detection parameter in the current detection period.

If the first displacement is not less than the first preset distance and is less than the second preset distance, it is indicated that the displacement of the intelligent robot in the current detection period may be abnormal or not, and the value of the specified detection parameter may be kept unchanged, that is, the first specified detection parameter of the previous detection period is used as the specified detection parameter of the current detection period.

If the first displacement is not smaller than the second preset distance, the displacement of the intelligent robot in the current detection period is non-abnormal, and the appointed detection parameter of the current detection period is set to be a preset numerical value representing that the displacement of the intelligent robot is in a non-abnormal state.

In one embodiment, referring to fig. 7, on the basis of fig. 1, step S103 may include:

s1031: if the current equipment performance of the intelligent robot is in an abnormal state, broadcasting and sending a second alarm signal in a third preset range, so that the alarm equipment in the third preset range alarms in a first alarm mode after receiving the second alarm signal;

and sending a message to a preset mobile terminal, wherein the message indicates that the current equipment performance of the intelligent robot is in an abnormal state.

S1032: and if the second alarm releasing signal is not received within the second preset time after the second alarm signal is sent, broadcasting and sending the second alarm signal within a fourth preset range, so that the alarm equipment within the fourth preset range alarms in the first alarm mode after receiving the second alarm signal.

Wherein the fourth preset range is greater than the third preset range.

In step S1031, reference may be made to the description of step S3031 above.

The detection device may further comprise a mobile communication module. And sending a message indicating that the current equipment performance of the intelligent robot is in an abnormal state to a preset mobile terminal through a mobile communication module.

The abnormal state of the intelligent robot can be divided into an abnormal state of the equipment performance and an abnormal state of the working environment.

The problem can be solved by field workers under the condition that the working environment is in an abnormal state, so that when the detection equipment detects that the working environment of the intelligent robot is in the abnormal state, the alarm signal can be broadcasted through the short-distance communication module, the alarm equipment gives an alarm, the field workers can timely maintain the intelligent robot, and the abnormal state of the working environment of the intelligent robot is relieved.

For the case that the equipment performance is in an abnormal state, because the equipment performance is in the abnormal state due to internal reasons of the intelligent robot, a field worker may not be able to solve the problem, and a professional technician needs to solve the problem. Therefore, when the detection device detects that the performance of the intelligent robot device is in an abnormal state, the detection device can broadcast an alarm signal through the short-distance communication module to enable the alarm device to give an alarm, and the alarm signal is sent to a mobile terminal of a professional technician through the mobile communication module to indicate that the current device performance of the intelligent robot is in the abnormal state, so that the professional technician can maintain the intelligent robot in time to remove the abnormal state of the device performance of the intelligent robot.

In step S1032, reference may be made to the description of step S3032 above.

In an embodiment, referring to fig. 8, fig. 8 is a flowchart of an example of a state detection method for an intelligent robot according to an embodiment of the present invention.

When the intelligent robot starts, the detection equipment also starts simultaneously. The detection device can periodically detect the device performance parameters and the working environment parameters of the intelligent robot, wherein the device performance parameters correspond to the first device state data, and the working environment parameters correspond to the second device state data.

And if the detection equipment detects that the equipment performance parameters are abnormal, indicating that the current equipment performance of the intelligent robot is in an abnormal state. And at the moment, the detection equipment controls the intelligent robot to stop working, broadcasts and sends a second alarm signal in a third preset range, and sends a message indicating that the equipment performance is abnormal to a mobile terminal of a technician. When the second alarm signal is received, the alarm device lights up the red light, and the buzzer sounds a second alarm sound indicating that the device performance is abnormal at a second frequency.

The detection device can be provided with a reset button for releasing the alarm, and when a worker presses the reset button, the detection device can receive the alarm releasing signal.

If the detection device sends the alarm signal within a second preset time (for example, 30 seconds), and the second alarm release signal is not detected, it indicates that the worker does not find the alarm of the alarm device, and the detection device may broadcast and send a fourth alarm signal within a fourth preset range, where the fourth preset range is greater than the third preset range, so that the alarm device at a farther distance sends an alarm, and the worker can find the alarm of the alarm device as soon as possible.

The alarm device, having received the fourth alarm signal, may sound a fourth alarm at a fourth frequency, wherein the fourth frequency is greater than the second frequency. And if the detection equipment detects that the working environment parameters are abnormal, the current working environment of the intelligent robot is in an abnormal state. At the moment, the detection equipment controls the intelligent robot to stop working, and broadcasts and sends a first alarm signal within a first preset range. When the alarm device receives the first alarm signal, the yellow lamp is turned on, and the buzzer sounds a first alarm sound indicating that the working environment is abnormal at a first frequency.

If the detection device sends the alarm signal within a first preset time (for example, 30 seconds), and the first alarm release signal is not detected, it indicates that the worker does not find the alarm of the alarm device, and the detection device may broadcast and send a third alarm signal to a second preset range, where the third preset range is greater than the first preset range, so that the alarm device at a farther distance sends an alarm, and the worker can find the alarm of the alarm device as soon as possible.

The alarm device receiving the third alarm signal may sound a third alarm at a third frequency, wherein the third frequency is greater than the first frequency.

And if the detection equipment does not detect that the equipment performance parameters and the working environment parameters are abnormal, continuing to periodically detect.

And if the detection equipment receives the alarm removing signal, the alarm is removed, wherein the alarm removing signal indicates that a worker is processing the abnormal condition or waiting for a technician to process the abnormal condition.

In an embodiment, referring to fig. 9, fig. 9 is a schematic diagram illustrating a state detection principle of an intelligent robot according to an embodiment of the present invention.

In fig. 9, the architecture may include a detection device 901, a technician mobile terminal 902, and an alarm cluster 903.

The detection apparatus 901 may include: a reset module 9011, a sensor module 9012, a data processing module 9013, a mobile communication module 9014, and a short-range communication module 9015.

The alarm cluster 903 may include a plurality of alarm devices, each of which includes a buzzer and a two-color warning light.

The data processing module 9013 is configured to acquire current first device state data of the intelligent robot to be detected, and determine whether the current device performance of the intelligent robot is in an abnormal state according to the first device state data and a preset abnormal working state identification condition.

If the data processing module 9013 determines that the current device performance of the intelligent robot is in an abnormal state, a second alarm message is sent to alarm devices within a third preset range through the short-distance communication module 9015. And the alarm equipment receiving the second alarm message alarms in the first alarm mode. The mobile communication module 9014 sends a message indicating that the current device performance of the intelligent robot is in an abnormal state to the technician mobile terminal 902.

If a worker uses the reset module 9011, the reset module 9011 sends an alarm release signal to the data processing module 9013, and the detection device 901 releases the alarm.

If the data processing module 9013 does not receive the alarm release signal sent by the reset module 9011 after the second preset duration, a second alarm message is sent to the alarm device within the fourth preset range through the short-distance communication module 9015, so that the alarm range is expanded.

The sensor module 9012 may include: the intelligent robot detection system comprises a temperature sensor, a level gauge and a displacement sensor, wherein the sensor module 9012 is used for periodically acquiring the current environment temperature, the current inclination angle and the displacement of the intelligent robot in the current detection period of the intelligent robot, and transmitting the acquired data to the data processing module 9013.

The data processing module 9013 determines the designated detection parameter of the current detection period according to the designated detection parameter of the previous detection period and the displacement of the intelligent robot in the current detection period. The second device state data of the current detection period is the current environment temperature of the intelligent robot, the current inclination angle of the intelligent robot and the specified detection parameters of the current detection period.

The data processing module 9013 determines whether the current working environment of the intelligent robot is in an abnormal state or not based on the second device state data and the preset abnormal working environment recognition condition.

If the data processing module 9013 determines that the current working environment of the intelligent robot is in an abnormal state, a first alarm message is sent to alarm equipment within a first preset range through the short-distance communication module 9015. And the alarm equipment receiving the first alarm message alarms in a second alarm mode.

If the data processing module 9013 does not receive the alarm release signal sent by the reset module 9011 after the first preset duration, the short-distance communication module 9015 sends a first alarm message to the alarm device in the second preset range, so that the alarm range is expanded.

Based on the same inventive concept, the embodiment of the invention also provides a state detection device of the intelligent robot. Referring to fig. 10, fig. 10 is a structural diagram of a state detection apparatus of an intelligent robot according to an embodiment of the present application, where the apparatus includes:

a first device status data acquiring module 1001, configured to acquire current first device status data of an intelligent robot to be detected; wherein the first device state data comprises: receiving the time length between the moment of sending the heartbeat message last time and the current moment, the occupancy rate of a memory and the utilization rate of a CPU;

the device performance determining module 1002 is configured to determine whether the current device performance of the intelligent robot is in an abnormal state according to the first device state data and a preset abnormal working state identification condition;

the first warning module 1003 is configured to perform warning in a first warning manner if the current device performance of the intelligent robot is in an abnormal state.

In one embodiment, the device performance determining module 1002 includes:

the first similarity determining submodule is used for calculating the similarity between the first to-be-detected feature vector and a first abnormal feature vector corresponding to the preset abnormal equipment performance;

and the device performance non-abnormal state determining submodule is further used for determining that the current device performance of the intelligent robot is in a non-abnormal state if the calculated similarity is not greater than the first threshold.

In one embodiment, the apparatus further comprises:

the second equipment state data acquisition module is used for acquiring second equipment state data of the intelligent robot in the current detection period when the preset detection period is reached; wherein the second device status data comprises at least one of: the method comprises the following steps of (1) setting the current ambient temperature of the intelligent robot, the current inclination angle of the intelligent robot and specified detection parameters of the current detection period; the specified detection parameters of the current detection period are as follows: the displacement detection parameters are determined based on the displacement detection parameters of the last detection period and the displacement of the intelligent robot in the current detection period;

and the second alarm module is used for giving an alarm in a second alarm mode if the current working environment of the intelligent robot is in an abnormal state.

In one embodiment, the work environment determination module includes:

the second similarity determining submodule is used for calculating the similarity between the second characteristic vector to be detected and a second abnormal characteristic vector corresponding to the preset abnormal working environment;

In one embodiment, the second warning module is specifically configured to broadcast and send a first warning signal in a first preset range if the current working environment of the intelligent robot is in an abnormal state, so that the warning device in the first preset range performs warning in a second warning manner after receiving the first warning signal;

if the first alarm releasing signal is not received within the first preset time after the first alarm signal is sent, the first alarm signal is broadcast and sent within a second preset range, so that the alarm equipment within the second preset range alarms in a second alarm mode after receiving the first alarm signal; wherein the second preset range is larger than the first preset range.

In one embodiment, the apparatus further comprises:

the specified detection parameter determining module is further used for taking the first specified detection parameter as the specified detection parameter of the current detection period if the first displacement is not smaller than the first preset distance and is smaller than the second preset distance; wherein the first preset distance is smaller than the second preset distance;

and the appointed detection parameter determining module is further used for setting the appointed detection parameter of the current detection period as a preset numerical value which represents that the displacement of the intelligent robot is in a non-abnormal state if the first displacement is not smaller than the second preset distance.

In one embodiment, the first alarm module 1003 is specifically configured to broadcast and send a second alarm signal in a third preset range if the current device performance of the intelligent robot is in an abnormal state, so that the alarm device in the third preset range performs an alarm in a first alarm manner after receiving the second alarm signal; sending a message to a preset mobile terminal, wherein the message indicates that the current equipment performance of the intelligent robot is in an abnormal state;

if the second alarm release signal is not received within a second preset time after the second alarm signal is sent, broadcasting and sending the second alarm signal within a fourth preset range, so that the alarm equipment within the fourth preset range alarms in a first alarm mode after receiving the second alarm signal; wherein the fourth preset range is greater than the third preset range.

An embodiment of the present invention further provides an electronic device, as shown in fig. 11, including a processor 1101, a communication interface 1102, a memory 1103 and a communication bus 1104, where the processor 1101, the communication interface 1102 and the memory 1103 complete mutual communication through the communication bus 1104,

a memory 1103 for storing a computer program;

the processor 1101 is configured to implement the following steps when executing the program stored in the memory 1103:

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.

In another embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the state detection method of the intelligent robot described in any of the above embodiments.

In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method for detecting the state of an intelligent robot as described in any of the above embodiments.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus, the electronic device, the computer-readable storage medium and the computer program product, since they are substantially similar to the method embodiments, the description is relatively simple, and in relation to the description, reference may be made to some parts of the description of the method embodiments.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A state detection method of an intelligent robot, characterized by comprising:

2. The method of claim 1, wherein determining whether the current device performance of the intelligent robot is in an abnormal state according to the first device state data and a preset abnormal working state identification condition comprises:

3. The method of claim 1, further comprising:

4. The method of claim 3, wherein determining whether the current working environment of the intelligent robot is in an abnormal state based on the second device state data and a preset abnormal working environment recognition condition comprises:

5. The method according to claim 3, wherein if the current working environment of the intelligent robot is in an abnormal state, the alarming in a second alarming mode comprises:

6. The method of claim 3, further comprising:

and if the first displacement is not less than a second preset distance, setting the specified detection parameter of the current detection period as a preset numerical value representing that the displacement of the intelligent robot is in a non-abnormal state.

7. The method according to claim 1, wherein if the current device performance of the intelligent robot is in an abnormal state, alarming in a first alarming mode comprises:

8. A state detection apparatus of an intelligent robot, the apparatus comprising:

9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any of claims 1 to 7 when executing a program stored in the memory.

10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.